security-review
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it is designed to analyze untrusted codebases.
- Ingestion points: Source code files (.js, .ts, .py) and configuration files (.env, package.json) searched by the agent.
- Boundary markers: Absent; the skill lacks instructions to delineate external file content from the agent's internal reasoning.
- Capability inventory: Execution of system commands including grep, npm, pip, and snyk for security auditing.
- Sanitization: None; the skill does not provide mechanisms to sanitize or escape the content of analyzed files.
- [COMMAND_EXECUTION]: The skill instructs the agent to run various shell commands to identify security flaws.
- Evidence: Extensive use of complex grep commands for pattern matching and instructions to use audit tools like npm audit, pip-audit, and snyk test.
Audit Metadata