rick-plan-improve
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs localized file operations and standard development commands without any detected malicious patterns.
- [COMMAND_EXECUTION]: Uses
git branch --show-currentto automatically resolve paths based on the active development branch. This is a benign use of system tools for workflow automation. - [PROMPT_INJECTION]: The skill processes plan files and intel dossiers, which are ingestion points for external data. While this represents a surface for potential indirect prompt injection, the agent's capabilities are limited to editing markdown files in a specific directory structure, presenting minimal risk.
- [DATA_EXFILTRATION]: No network operations or unauthorized data transfers were identified. The skill only reads project-related documentation and writes back to specified versioned paths.
Audit Metadata