skill-audit
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a methodical process for auditing codebases by ingesting external source files via search tools like Glob and Grep. This functionality introduces a potential surface for indirect prompt injection attacks, where malicious content embedded in the source code could attempt to influence the auditing agent's findings or behavior.
- Ingestion points: External codebase files and application features identified during the discovery and execution phases in SKILL.md.
- Boundary markers: The instructions do not specify the use of delimiters or warnings to separate audited data from the agent's internal logic.
- Capability inventory: The agent uses filesystem search tools (Glob, Grep) and operates within a shell environment using available subagent tools.
- Sanitization: No procedures for sanitizing or escaping the content of audited files are provided in the skill instructions.
Audit Metadata