Prompt-injection style instruction pattern detected.
Warn
- Code
- suspicious.prompt_injection_instructions
- Location
- README.md:69
Security audit
Security checks across malware telemetry and agentic risk
This looks like a legitimate local prompt-injection guardrail, but the package is incomplete enough that it may fail open while claiming protection.
Install only if you treat it as an incomplete advisory guardrail. Before relying on it, add or obtain audited rule files, create .env yourself from trusted values, and do not assume it blocks prompt injection just because the wrapper scripts run.
67/67 vendors flagged this skill as clean.
Detected: suspicious.prompt_injection_instructions