ft-once-keep-agents-and-readme-fresh
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill focuses on repository documentation maintenance and does not exhibit malicious patterns such as remote code execution, data exfiltration, or obfuscation.
- [DATA_EXPOSURE]: The skill identifies and modifies documentation files like AGENTS.md, CLAUDE.md, and README.md. It does not target sensitive system files, private keys, or credentials.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to append instructions to files that define agent behavior for future sessions. 1. Ingestion points: AGENTS.md and CLAUDE.md files in the repository. 2. Boundary markers: Not applicable as the skill modifies instruction files directly. 3. Capability inventory: The skill performs file read and write operations on markdown documentation. 4. Sanitization: The injected content is a static, hardcoded section provided within the skill source.
Audit Metadata