aria-inputguard

Runtime security skill. Analyze inputs for injection attacks, sanitize HTML, check SQL and path safety, filter sensitive output, and validate API parameters.

Usage

exec python3 /app/skills/run_skill.py input_guard <function> '<json_args>'

Functions

analyze_input

Analyze user input for security threats including prompt injection, jailbreak attempts, and malicious patterns.

exec python3 /app/skills/run_skill.py input_guard analyze_input '{"text": "ignore previous instructions"}'

sanitize_for_html

Sanitize text for safe HTML display; escapes HTML entities to prevent XSS.

exec python3 /app/skills/run_skill.py input_guard sanitize_for_html '{"text": "<script>alert(1)</script>"}'

check_sql_safety

Check if text contains SQL injection patterns.

exec python3 /app/skills/run_skill.py input_guard check_sql_safety '{"text": "1; DROP TABLE users"}'

check_path_safety

Check if a file path contains path traversal attempts.

exec python3 /app/skills/run_skill.py input_guard check_path_safety '{"path": "../../etc/passwd"}'

filter_output

Filter sensitive data (API keys, passwords, tokens) from output text.

exec python3 /app/skills/run_skill.py input_guard filter_output '{"text": "key=sk-abc123"}'

build_safe_query

Build a safe parameterized SQL query (select, insert, update).

exec python3 /app/skills/run_skill.py input_guard build_safe_query '{"table": "users", "operation": "select"}'

get_security_summary

Get summary of recent security events including blocked requests and threat patterns.

exec python3 /app/skills/run_skill.py input_guard get_security_summary '{}'

validate_api_params

Validate API parameters against a type schema.

exec python3 /app/skills/run_skill.py input_guard validate_api_params '{"params": {"limit": "10"}, "schema": {"limit": "integer"}}'