readme-writing
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill ingests data from external project files to populate a documentation template. 1. Ingestion points: Project configuration files (package.json, pyproject.toml, .env.example) and source code files. 2. Boundary markers: Absent; there are no instructions for the agent to ignore or delimit potentially malicious instructions within analyzed files. 3. Capability inventory: Reading local file contents and executing directory listing. 4. Sanitization: Absent; content from files is interpolated directly into the template.
- [Command Execution] (LOW): The skill uses the 'tree' command to extract the directory structure, which is a standard local operation but constitutes execution of system utilities.
Audit Metadata