studio-develop-refactor-plan
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface as it is designed to read and process external repository content and documentation files to create its migration plans. Ingestion points: Reads content from docs/PRD.md, docs/PRODUCT.md, docs/DESIGN.md, docs/ROADMAP.md, and the general codebase (SKILL.md). Boundary markers: The instructions do not define specific delimiters to prevent the agent from potentially interpreting embedded instructions within the source documents or code. Capability inventory: The skill possesses file read capabilities across the repository and file write capabilities for docs/PRD.md and docs/REFACTOR.md. Sanitization: There are no explicit requirements in the skill to sanitize or validate the content retrieved from the processed files.
Audit Metadata