sast-patterns
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructions create a surface for indirect prompt injection by having the agent process untrusted code.\n
- Ingestion points: The agent is directed to scan and review source code files (SKILL.md).\n
- Boundary markers: The instructions lack delimiters or explicit warnings for the agent to ignore instructions embedded in code comments or strings.\n
- Capability inventory: The skill references capabilities for file reading, command execution (semgrep), and CI/CD integration (SKILL.md).\n
- Sanitization: No sanitization or validation of the ingested code content is defined.\n- [EXTERNAL_DOWNLOADS]: References to security auditing tools and documentation target well-known and reputable services such as GitHub, Semgrep, and OWASP.\n- [COMMAND_EXECUTION]: Provides standard CLI command examples for security auditing (e.g., semgrep, npm audit, pip-audit) intended for development and security testing workflows.
Audit Metadata