install
source · Clone the upstream repo
git clone https://github.com/openclaw/skills
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/openclaw/skills "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/blackworm/prompt-injection-protection" ~/.claude/skills/clawdbot-skills-prompt-injection-protection && rm -rf "$T"
manifest:
skills/blackworm/prompt-injection-protection/SKILL.mdsource content
Prompt Injection Protection Skill
Description
A comprehensive skill to protect against prompt injection attacks when processing external content such as websites, emails, documents, and other untrusted input sources.
Purpose
This skill provides methods to safely sanitize, validate, and process external content to prevent malicious prompt injection attempts that could manipulate the AI's behavior or cause it to execute unintended actions.
Features
- Content sanitization and validation
- Prompt injection detection and filtering
- Secure processing of web content
- Safe extraction of information from untrusted sources
- Protection against jailbreak attempts
Security Measures
- Input sanitization
- Output encoding
- Context isolation
- Validation of external content
- Prevention of instruction hijacking
Usage
The skill provides functions to:
- Sanitize external content before processing
- Validate content against injection patterns
- Safely extract information from untrusted sources
- Process web content securely
- Filter potentially harmful instructions