crafting-effective-readmes
Pass
Audited by Gen Agent Trust Hub on May 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were identified. The skill is composed of informational guidelines and markdown templates for various project types.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it is designed to ingest and analyze user project data (e.g., package.json, main source files, and current README content) to generate or refresh documentation. Ingestion points occur during the 'Reviewing/refreshing' phase where the agent reads the project state. While boundary markers and explicit sanitization are absent, the risk is assessed as low given that the skill's capabilities are focused on text generation and do not involve execution of the processed data.
Audit Metadata