variant-analysis
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill guides the use of
ripgrep(rg) for pattern-based code searching, which is standard behavior for code auditing.- [PROMPT_INJECTION]: The skill includes a safety gate requiring user confirmation of authorization and scope before performing probes or exploits, which acts as a protection against unauthorized agent behavior.- [PROMPT_INJECTION]: The skill ingests untrusted codebase data for analysis. This creates an indirect prompt injection surface where instructions hidden in the code could attempt to influence the agent.
Audit Metadata