super-plan
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified. The skill's behavior is consistent with its stated goal of project planning and includes safety-conscious rules such as forbidding code execution while planning and requiring user confirmation before saving files.
- [PROMPT_INJECTION]: The skill processes untrusted repository content to inform the planning process. The following characteristics were noted regarding indirect injection surfaces:
- Ingestion points: Reads files from the local repository during the 'Explore the codebase' phase (SKILL.md).
- Boundary markers: None identified for distinguishing between instructions and repository data.
- Capability inventory: Limited to file system read access for exploration and write access for creating plan files (PLAN.md, plans/*.md). No command execution or network capabilities are defined.
- Sanitization: No explicit sanitization of repository content was found.
Audit Metadata