qrspi-iterate-plan
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a structured workflow for refining implementation plans based on user feedback and codebase state. It uses restricted tools for reading and editing files in specific directories.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) as it processes external plan files and user feedback to inform its edits.
- Ingestion points: It reads plan documents from
thoughts/shared/plans/and processes user-provided feedback strings. - Boundary markers: None explicitly defined in the instructions to separate data from commands.
- Capability inventory: The skill has the ability to read files, write/edit files (via the Edit tool), and invoke a
codebase-analyzeragent. - Sanitization: No explicit sanitization or validation of the input data is mentioned. While the surface exists, this is standard functionality for an AI-driven development tool and does not indicate malicious intent.
Audit Metadata