audit
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted content from local repositories, branches, and diffs. This creates a theoretical surface for indirect prompt injection if the project being audited contains adversarial instructions.
- Ingestion points: Repository files, documentation, and codebases processed during the audit.
- Boundary markers: No specific delimiters or "ignore instructions" warnings are defined in the workflow.
- Capability inventory: The skill may execute local scripts (e.g., tests, linters) and modify documentation files.
- Sanitization: The workflow does not explicitly describe sanitization for ingested content.
- [COMMAND_EXECUTION]: The workflow instructs the agent to locate and execute "safe" or "non-destructive" commands such as tests or linters. This is standard behavior for an auditing tool, though it relies on the integrity of the configuration files within the audited project.
Audit Metadata