init
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository (README, codebase, and rule files) to generate instructions that guide future AI agent sessions.
- Ingestion points: Analyzes the codebase, README.md, .cursor/rules/, .cursorrules, and .github/copilot-instructions.md as specified in SKILL.md.
- Capability inventory: The skill creates or updates the CLAUDE.md file in the local workspace, which influences agent behavior in future interactions (SKILL.md).
- Boundary markers: The instructions do not define delimiters or markers to isolate ingested content from the generated instructions.
- Sanitization: No explicit sanitization, filtering, or validation of the ingested content is described in the instructions.
Audit Metadata