setup
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted repository data to establish project context, creating an ingestion surface for indirect prompt injection.
- Ingestion points: The skill reads repository contents including manifests, documentation, and existing agent rules in AGENTS.md.
- Boundary markers: Utilizes managed blocks in AGENTS.md to delimit its modifications and preserve human content.
- Capability inventory: The skill is capable of performing file system writes to create navigation and context artifacts such as AGENTS.md and project.md.
- Sanitization: The documentation does not describe explicit sanitization or filtering of the content ingested from repository files before it is processed by the agent.
Audit Metadata