redesign-existing-projects
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to scan and read external codebases as its primary ingestion point. Malicious instructions embedded within the codebase being audited (e.g., in code comments or documentation) could potentially influence the agent's behavior during the 'Fix' or 'Output Report' phases.
- Ingestion points: The skill instructions specify 'Scan — Read the codebase' to identify frameworks and patterns.
- Boundary markers: There are no explicit instructions for the agent to use delimiters or to ignore embedded instructions within the source code being analyzed.
- Capability inventory: The skill possesses file-write capabilities, as it is instructed to 'Apply targeted upgrades' to the existing codebase and write report files to the
llmwiki/directory. - Sanitization: The instructions do not mention sanitizing or escaping content from the codebase before it is used to generate the Output Report or modify files.
- [EXTERNAL_DOWNLOADS]: The skill recommends the use of
https://picsum.photos/for generating placeholder imagery. This is a well-known and standard service for design prototyping and does not represent a security risk in this context.
Audit Metadata