project-planning
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE] (SAFE): The skill is entirely composed of markdown instructions for the AI agent and does not include any Python scripts, Node.js code, or binary executables.
- [PROMPT_INJECTION] (SAFE): Analysis of the instructions shows no evidence of adversarial patterns, such as 'ignore previous instructions' or attempts to bypass safety filters.
- [DATA_EXFILTRATION] (SAFE): No network operations (e.g., curl, fetch) or hardcoded credentials were found. The skill only interacts with localized project files (
project-plan.md,project-state.md). - [COMMAND_EXECUTION] (SAFE): There are no commands that interact with the underlying operating system or shell environment.
- [REMOTE_CODE_EXECUTION] (SAFE): The skill does not download or execute any external scripts or packages.
Audit Metadata