check-claude-md
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies and processes technical decisions from untrusted project files and conversation history to generate configuration updates.
- Ingestion points: The skill reviews the conversation history and modified/created files in the project to extract project knowledge (SKILL.md, Phase 1).
- Boundary markers: Not present; there are no instructions for the agent to use delimiters or specific markers to isolate the code being analyzed from the agent's instructions.
- Capability inventory: The skill utilizes file system read capabilities, user interaction via AskUserQuestion, and file modification using the Edit tool to update CLAUDE.md.
- Sanitization: Not present; the skill does not explicitly mention validating or escaping the content retrieved from the code analysis phase before presenting it as suggestions or applying updates.
Audit Metadata