redesign-existing-projects
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to scan, diagnose, and modify existing codebases, which serves as an ingestion point for untrusted data. Malicious instructions embedded in the code being redesigned (e.g., in comments or strings) could potentially influence the agent's behavior.
- Ingestion points: Project codebase files are read in the "Scan" phase (Step 1).
- Boundary markers: Absent. There are no instructions defining boundaries or warning the agent to disregard instructions found within the files it audits.
- Capability inventory: The skill allows for reading files and applying targeted upgrades/writes to the existing stack (Step 3).
- Sanitization: Absent. The skill acts directly on the content of the project files.
- [EXTERNAL_DOWNLOADS]: The skill suggests fetching placeholder images from
picsum.photos. This is a well-known and standard service for generating placeholder assets in web development and is used here for legitimate UI/UX prototyping purposes.
Audit Metadata