project-onboarding
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: No malicious behavior or security bypass attempts detected. All requested permissions (Read, Write, Bash) are justified by the skill's purpose of IDE project management.
- [COMMAND_EXECUTION]: The skill utilizes the Bash tool for project setup, including git operations. This is a declared capability within the skill metadata.
- [PROMPT_INJECTION]: Identified an attack surface for indirect prompt injection as the skill scans local project data. 1. Ingestion points: Local project structure and .idea configuration files (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Bash execution and file write permissions (meta.json). 4. Sanitization: No sanitization of project content is mentioned.
Audit Metadata