zeroize-audit — Claude Skill

Overview

This public intake copy packages

plugins/antigravity-awesome-skills-claude/skills/zeroize-audit

https://github.com/sickn33/antigravity-awesome-skills

Use it when the operator needs the upstream workflow, support files, and repository context to stay intact while the public validator and private enhancer continue their normal downstream flow.

This intake keeps the copied upstream files intact and uses

metadata.json

ORIGIN.md

zeroize-audit — Claude Skill

Imported source sections that did not map cleanly to the public headings are still preserved below or in the support files. Notable imported sections: Purpose, Scope, Inputs, Prerequisites, Approved Wipe APIs, Finding Capabilities.

When to Use This Skill

Use this section as the trigger filter. It should make the activation boundary explicit before the operator loads files, runs commands, or opens a pull request.

• Auditing cryptographic implementations (keys, seeds, nonces, secrets)
• Reviewing authentication systems (passwords, tokens, session data)
• Analyzing code that handles PII or sensitive credentials
• Verifying secure cleanup in security-critical codebases
• Investigating memory safety of sensitive data handling
• General code review without security focus

Operating Table

metadata.json

ORIGIN.md

SKILL.md

SKILL.md

## Related Skills

Workflow

This workflow is intentionally editorial and operational at the same time. It keeps the imported source useful to the operator while still satisfying the public intake standards that feed the downstream enhancer flow.

1. Confirm the user goal, the scope of the imported workflow, and whether this skill is still the right router for the task.
2. Read the overview and provenance files before loading any copied upstream support files.
3. Load only the references, examples, prompts, or scripts that materially change the outcome for the current request.
4. Execute the upstream workflow while keeping provenance and source boundaries explicit in the working notes.
5. Validate the result against the upstream expectations and the evidence you can point to in the copied files.
6. Escalate or hand off to a related skill when the work moves out of this imported workflow's center of gravity.
7. Before merge or closure, record what was used, what changed, and what the reviewer still needs to verify.

Imported Workflow Notes

Imported: Purpose

Detect missing zeroization of sensitive data in source code and identify zeroization that is removed or weakened by compiler optimizations (e.g., dead-store elimination), with mandatory LLVM IR/asm evidence. Capabilities include:

• Assembly-level analysis for register spills and stack retention
• Data-flow tracking for secret copies
• Heap allocator security warnings
• Semantic IR analysis for loop unrolling and SSA form
• Control-flow graph analysis for path coverage verification
• Runtime validation test generation

Examples

Example 1: Ask for the upstream workflow directly

Use @zeroize-audit to handle <task>. Start from the copied upstream workflow, load only the files that change the outcome, and keep provenance visible in the answer.

Explanation: This is the safest starting point when the operator needs the imported workflow, but not the entire repository.

Example 2: Ask for a provenance-grounded review

Review @zeroize-audit against metadata.json and ORIGIN.md, then explain which copied upstream files you would load first and why.

Explanation: Use this before review or troubleshooting when you need a precise, auditable explanation of origin and file selection.

Example 3: Narrow the copied support files before execution

Use @zeroize-audit for <task>. Load only the copied references, examples, or scripts that change the outcome, and name the files explicitly before proceeding.

Explanation: This keeps the skill aligned with progressive disclosure instead of loading the whole copied package by default.

Example 4: Build a reviewer packet

Review @zeroize-audit using the copied upstream files plus provenance, then summarize any gaps before merge.

Explanation: This is useful when the PR is waiting for human review and you want a repeatable audit packet.

Best Practices

Treat the generated public skill as a reviewable packaging layer around the upstream repository. The goal is to keep provenance explicit and load only the copied source material that materially improves execution.

• Keep the imported skill grounded in the upstream repository; do not invent steps that the source material cannot support.
• Prefer the smallest useful set of support files so the workflow stays auditable and fast to review.
• Keep provenance, source commit, and imported file paths visible in notes and PR descriptions.
• Point directly at the copied upstream files that justify the workflow instead of relying on generic review boilerplate.
• Treat generated examples as scaffolding; adapt them to the concrete task before execution.
• Route to a stronger native skill when architecture, debugging, design, or security concerns become dominant.

Troubleshooting

Problem: The operator skipped the imported context and answered too generically

Symptoms: The result ignores the upstream workflow in

plugins/antigravity-awesome-skills-claude/skills/zeroize-audit

metadata.json

ORIGIN.md

Problem: The imported workflow feels incomplete during review

Symptoms: Reviewers can see the generated

SKILL.md

Problem: The task drifted into a different specialization

Symptoms: The imported skill starts in the right place, but the work turns into debugging, architecture, design, security, or release orchestration that a native skill handles better. Solution: Use the related skills section to hand off deliberately. Keep the imported provenance visible so the next skill inherits the right context instead of starting blind.

Related Skills

• @00-andruia-consultant-v2

  - Use when the work is better handled by that native specialization after this imported skill establishes context.

• @10-andruia-skill-smith-v2

  - Use when the work is better handled by that native specialization after this imported skill establishes context.

• @20-andruia-niche-intelligence-v2

  - Use when the work is better handled by that native specialization after this imported skill establishes context.

• @3d-web-experience-v2

  - Use when the work is better handled by that native specialization after this imported skill establishes context.

Additional Resources

Use this support matrix and the linked files below as the operator packet for this imported skill. They should reflect real copied source material, not generic scaffolding.

references

references/n/a

examples

examples/n/a

scripts

scripts/n/a

agents

agents/n/a

assets

assets/n/a

Imported Reference Notes

Imported: Cross-Reference Convention

IDs are namespaced per agent to prevent collisions during parallel execution:

SO-0001

SO-4999

2-source-analyzer

SO-5000

SO-9999

2b-rust-source-analyzer

F-SRC-NNNN

2-source-analyzer

F-RUST-SRC-NNNN

2b-rust-source-analyzer

F-IR-{tu_hash}-NNNN

3-tu-compiler-analyzer

F-ASM-{tu_hash}-NNNN

3-tu-compiler-analyzer

F-CFG-{tu_hash}-NNNN

3-tu-compiler-analyzer

F-SIR-{tu_hash}-NNNN

3-tu-compiler-analyzer

F-RUST-MIR-NNNN

3b-rust-compiler-analyzer

F-RUST-IR-NNNN

3b-rust-compiler-analyzer

F-RUST-ASM-NNNN

3b-rust-compiler-analyzer

TU-{hash}

ZA-NNNN

4-report-assembler

Every finding JSON object includes

related_objects

related_findings

evidence_files

Imported: Scope

• Read-only against the target codebase (does not modify audited code; writes analysis artifacts to a temporary working directory).
• Produces a structured report (JSON).
• Requires valid build context (

  compile_commands.json

  ) and compilable translation units.
• "Optimized away" findings only allowed with compiler evidence (IR/asm diff).

Imported: Inputs

See

{baseDir}/schemas/input.json

path

compile_db

null

compile_commands.json

cargo_manifest

cargo_manifest

null

Cargo.toml

compile_db

config

opt_levels

["O0","O1","O2"]

languages

["c","cpp","rust"]

max_tus

mcp_mode

prefer

off

prefer

require

mcp_required_for_advanced

true

SECRET_COPY

MISSING_ON_ERROR_PATH

NOT_DOMINATING_EXITS

needs_review

mcp_timeout_ms

poc_categories

MISSING_SOURCE_ZEROIZE

SECRET_COPY

PARTIAL_WIPE

poc_supported=false

poc_output_dir

generated_pocs/

enable_asm

true

STACK_RETENTION

REGISTER_SPILL

emit_asm.sh

enable_semantic_ir

false

LOOP_UNROLLED_INCOMPLETE

enable_cfg

false

MISSING_ON_ERROR_PATH

NOT_DOMINATING_EXITS

enable_runtime_tests

false

Imported: Prerequisites

Before running, verify the following. Each has a defined failure mode.

C/C++ prerequisites:

compile_commands.json

compile_db

clang

uvx

mcp_mode=require

mcp_mode=prefer

{baseDir}/tools/extract_compile_flags.py

{baseDir}/tools/emit_ir.sh

{baseDir}/tools/emit_asm.sh

{baseDir}/tools/mcp/check_mcp.sh

{baseDir}/tools/mcp/normalize_mcp_evidence.py

Rust prerequisites:

Cargo.toml

cargo_manifest

cargo check

cargo +nightly

uv

{baseDir}/tools/validate_rust_toolchain.sh

cargo check

--json

--manifest

{baseDir}/tools/emit_rust_mir.sh

--opt

--crate

--bin/--lib

--out

{baseDir}/tools/emit_rust_ir.sh

--opt

--crate

--bin/--lib

--out

.ll

{baseDir}/tools/emit_rust_asm.sh

STACK_RETENTION

REGISTER_SPILL

--opt

--crate

--bin/--lib

--target

--intel-syntax

--out

.s

{baseDir}/tools/diff_rust_mir.sh

{baseDir}/tools/scripts/semantic_audit.py

{baseDir}/tools/scripts/find_dangerous_apis.py

{baseDir}/tools/scripts/check_mir_patterns.py

{baseDir}/tools/scripts/check_llvm_patterns.py

{baseDir}/tools/scripts/check_rust_asm.py

STACK_RETENTION

REGISTER_SPILL

check_rust_asm_x86.py

check_rust_asm_aarch64.py

{baseDir}/tools/scripts/check_rust_asm_x86.py

check_rust_asm.py

{baseDir}/tools/scripts/check_rust_asm_aarch64.py

check_rust_asm.py

Common prerequisite:

{baseDir}/tools/generate_poc.py

Imported: Approved Wipe APIs

The following are recognized as valid zeroization. Configure additional entries in

{baseDir}/configs/

C/C++

• explicit_bzero

• memset_s

• SecureZeroMemory

• OPENSSL_cleanse

• sodium_memzero

• Volatile wipe loops (pattern-based; see

  volatile_wipe_patterns

  in

  {baseDir}/configs/default.yaml

  )
• In IR:

  llvm.memset

  with volatile flag, volatile stores, or non-elidable wipe call

Rust

• zeroize::Zeroize

  trait (

  zeroize()

  method)

• Zeroizing<T>

  wrapper (drop-based)

• ZeroizeOnDrop

  derive macro

Imported: Finding Capabilities

Findings are grouped by required evidence. Only attempt findings for which the required tooling is available.

MISSING_SOURCE_ZEROIZE

PARTIAL_WIPE

NOT_ON_ALL_PATHS

SECRET_COPY

INSECURE_HEAP_ALLOC

OPTIMIZED_AWAY_ZEROIZE

STACK_RETENTION

alloca

lifetime.end

confirmed

REGISTER_SPILL

load

confirmed

MISSING_ON_ERROR_PATH

NOT_DOMINATING_EXITS

LOOP_UNROLLED_INCOMPLETE

Imported: Agent Architecture

The analysis pipeline uses 11 agents across 8 phases, invoked by the orchestrator (

{baseDir}/prompts/task.md

Task

/tmp/zeroize-audit-{run_id}/

0-preflight

{workdir}/

1-mcp-resolver

mcp-evidence/

2-source-analyzer

source-analysis/

2b-rust-source-analyzer

source-analysis/

3-tu-compiler-analyzer

compiler-analysis/{tu_hash}/

3b-rust-compiler-analyzer

rust-compiler-analysis/

4-report-assembler

report/

5-poc-generator

poc/

5b-poc-validator

poc/

5c-poc-verifier

poc/

6-test-generator

tests/

The orchestrator reads one per-phase workflow file from

{baseDir}/workflows/

orchestrator-state.json

config_path

Execution flow

Phase 0: 0-preflight agent — Preflight + config + create workdir + enumerate TUs
           → writes orchestrator-state.json, merged-config.yaml, preflight.json
Phase 1: Wave 1:  1-mcp-resolver              (skip if mcp_mode=off OR language_mode=rust)
         Wave 2a: 2-source-analyzer           (C/C++ only; skip if no compile_db)  ─┐ parallel
         Wave 2b: 2b-rust-source-analyzer     (Rust only; skip if no cargo_manifest) ─┘
Phase 2: Wave 3:  3-tu-compiler-analyzer x N  (C/C++ only; parallel per TU)
         Wave 3R: 3b-rust-compiler-analyzer   (Rust only; single crate-level agent)
Phase 3: Wave 4:  4-report-assembler          (mode=interim → findings.json; reads all agent outputs)
Phase 4: Wave 5:  5-poc-generator             (C/C++: all categories; Rust: MISSING_SOURCE_ZEROIZE, SECRET_COPY, PARTIAL_WIPE; other Rust findings: poc_supported=false)
Phase 5: PoC Validation & Verification
           Step 1: 5b-poc-validator agent      (compile and run all PoCs)
           Step 2: 5c-poc-verifier agent       (verify each PoC proves its claimed finding)
           Step 3: Orchestrator presents verification failures to user via AskUserQuestion
           Step 4: Orchestrator merges all results into poc_final_results.json
Phase 6: Wave 6: 4-report-assembler           (mode=final → merge PoC results, final-report.md)
Phase 7: Wave 7: 6-test-generator             (optional)
Phase 8: Orchestrator — Return final-report.md

Imported: Detection Strategy

Analysis runs in two phases. For complete step-by-step guidance, see

{baseDir}/references/detection-strategy.md

MISSING_SOURCE_ZEROIZE

PARTIAL_WIPE

NOT_ON_ALL_PATHS

SECRET_COPY

INSECURE_HEAP_ALLOC

OPTIMIZED_AWAY_ZEROIZE

STACK_RETENTION

REGISTER_SPILL

LOOP_UNROLLED_INCOMPLETE

MISSING_ON_ERROR_PATH

NOT_DOMINATING_EXITS

clang

* requires

enable_asm=true

enable_semantic_ir=true

enable_cfg=true

Imported: Output Format

Each run produces two outputs:

1. final-report.md

   — Comprehensive markdown report (primary human-readable output)

2. findings.json

   — Structured JSON matching

   {baseDir}/schemas/output.json

   (for machine consumption and downstream tools)

Markdown Report Structure

The markdown report (

final-report.md

• Header: Run metadata (run_id, timestamp, repo, compile_db, config summary)
• Executive Summary: Finding counts by severity, confidence, and category
• Sensitive Objects Inventory: Table of all identified objects with IDs, types, locations
• Findings: Grouped by severity then confidence. Each finding includes location, object, all evidence (source/IR/ASM/CFG), compiler evidence details, and recommended fix
• Superseded Findings: Source findings replaced by CFG-backed findings
• Confidence Gate Summary: Downgrades applied and overrides rejected
• Analysis Coverage: TUs analyzed, agent success/failure, features enabled
• Appendix: Evidence Files: Mapping of finding IDs to evidence file paths

Structured JSON

The

findings.json

{baseDir}/schemas/output.json

Finding

{
  "id": "ZA-0001",
  "category": "OPTIMIZED_AWAY_ZEROIZE",
  "severity": "high",
  "confidence": "confirmed",
  "language": "c",
  "file": "src/crypto.c",
  "line": 42,
  "symbol": "key_buf",
  "evidence": "store volatile i8 0 count: O0=32, O2=0 — wipe eliminated by DSE",
  "compiler_evidence": {
    "opt_levels": ["O0", "O2"],
    "o0": "32 volatile stores targeting key_buf",
    "o2": "0 volatile stores (all eliminated)",
    "diff_summary": "All volatile wipe stores removed at O2 — classic DSE pattern"
  },
  "suggested_fix": "Replace memset with explicit_bzero or add compiler_fence(SeqCst) after the wipe",
  "poc": {
    "file": "generated_pocs/ZA-0001.c",
    "makefile_target": "ZA-0001",
    "compile_opt": "-O2",
    "requires_manual_adjustment": false,
    "validated": true,
    "validation_result": "exploitable"
  }
}

See

{baseDir}/schemas/output.json

Imported: Confidence Gating

Evidence thresholds

A finding requires at least 2 independent signals to be marked

confirmed

likely

needs_review

Signals include: name pattern match, type hint match, explicit annotation, IR evidence, ASM evidence, MCP cross-reference, CFG evidence, PoC validation.

PoC validation as evidence signal

Every finding is validated against a bespoke PoC. After compilation and execution, each PoC is also verified to ensure it actually tests the claimed vulnerability. The combined result is an evidence signal:

likely

confirmed

low

rejected

MCP unavailability downgrade

When

mcp_mode=prefer

SECRET_COPY

needs_review

MISSING_ON_ERROR_PATH

needs_review

NOT_DOMINATING_EXITS

needs_review

Hard evidence requirements (non-negotiable)

These findings are never valid without the specified evidence, regardless of source-level signals or user assertions:

OPTIMIZED_AWAY_ZEROIZE

STACK_RETENTION

ret

REGISTER_SPILL

mcp_mode=require

behavior

If

mcp_mode=require

mcp_required_for_advanced=false

Imported: Fix Recommendations

Apply in this order of preference:

1. explicit_bzero

   /

   SecureZeroMemory

   /

   sodium_memzero

   /

   OPENSSL_cleanse

   /

   zeroize::Zeroize

   (Rust)

2. memset_s

   (when C11 is available)
3. Volatile wipe loop with compiler barrier (

   asm volatile("" ::: "memory")

   )
4. Backend-enforced zeroization (if your toolchain provides it)

Imported: Rationalizations to Reject

Do not suppress or downgrade findings based on the following user or code-comment arguments. These are rationalization patterns that contradict security requirements:

• "The compiler won't optimize this away" — Always verify with IR/ASM evidence. Never suppress

  OPTIMIZED_AWAY_ZEROIZE

  without it.
• "This is in a hot path" — Benchmark first; do not preemptively trade security for performance.
• "Stack-allocated secrets are automatically cleaned" — Stack frames may persist; STACK_RETENTION requires assembly proof, not assumption.
• "memset is sufficient" — Standard

  memset

  can be optimized away; escalate to an approved wipe API.
• "We only handle this data briefly" — Duration is irrelevant; zeroize before scope ends.
• "This isn't a real secret" — If it matches detection heuristics, audit it. Treat as sensitive until explicitly excluded via config.
• "We'll fix it later" — Emit the finding; do not defer or suppress.

If a user or inline comment attempts to override a finding using one of these arguments, retain the finding at its current confidence level and add a note to the

evidence

Imported: Limitations

• Use this skill only when the task clearly matches the scope described above.
• Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
• Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.