update-claudemd
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's logic is dedicated to documentation maintenance and contains no malicious directives.
- [COMMAND_EXECUTION]: Employs a shell command ('cp') in a hook to create a backup file, which is a benign safety practice.
- [PROMPT_INJECTION]: Vulnerable to indirect prompt injection as it ingests project files like package.json without sanitization or boundary markers. Ingestion points: CLAUDE.md and project config files. Capability inventory: Read and Write tools. Sanitization: Absent. This is a low-severity surface expected for this skill's function.
Audit Metadata