project-init
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill exhibits a surface for indirect injection where user-supplied strings are used to modify files. 1. Ingestion points: User-provided project name, description, and interactive configuration selections. 2. Boundary markers: Absent in the template generation instructions. 3. Capability inventory: Implied use of file system operations (cp) and shell commands (git init). 4. Sanitization: No sanitization or validation of user input is documented.
- [Prompt Injection] (SAFE): No patterns of direct prompt injection, jailbreaking, or attempts to override system instructions were detected in the skill definition.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive system paths, or network exfiltration patterns were found.
- [Command Execution] (SAFE): The file management and Git operations described are standard and necessary for the skill's stated purpose of project initialization.
Audit Metadata