claude-md-enhancer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Prompt Injection] (LOW): The skill exhibits an indirect prompt injection surface (Category 8) due to its core workflow of processing codebase metadata to generate documentation.\n- Ingestion points: Project files such as
package.jsonandREADME.mdare ingested to provide project context (as seen insample_input.json).\n- Boundary markers: No explicit delimiters are present in the provided templates to isolate ingested codebase content from the agent's instructions.\n- Capability inventory: The skill is designed to write to the local filesystem to create and updateCLAUDE.mdfiles.\n- Sanitization: No sanitization or escaping of the ingested project data is demonstrated in the provided templates or sample workflows.
Audit Metadata