redesign-existing-projects
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes the existing codebase of a project, which is considered untrusted data that could contain malicious instructions.
- Ingestion points: The agent reads the local codebase, including styling methods, framework patterns, and existing design logic during the 'Scan' phase in
SKILL.md. - Boundary markers: No explicit delimiters or 'ignore' instructions are used to separate the analyzed code content from the agent's execution logic.
- Capability inventory: The skill has the capability to modify existing project files (Fix phase) and write new markdown files to the
llmwiki/directory (Output Report phase). - Sanitization: The skill does not define specific sanitization or validation routines for the content ingested from the codebase before it is used to generate fixes or reports.
- [EXTERNAL_DOWNLOADS]: The skill references
https://picsum.photosas a source for high-quality placeholder images when actual project assets are unavailable.
Audit Metadata