redesign-existing-projects
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and process external codebase content ('Scan — Read the codebase') and then apply modifications ('Fix — Apply targeted upgrades'). This ingestion of untrusted data from existing projects creates a surface for indirect prompt injection if the project files contain malicious instructions meant to influence the agent.
- Ingestion points: The agent is instructed to read the entire codebase in the first step of the process.
- Boundary markers: There are no explicit instructions or delimiters used to warn the agent against following instructions embedded in the code it reads.
- Capability inventory: The skill allows for file writing and code modification across the project.
- Sanitization: No validation or sanitization of the input code is specified before the agent acts on it.
- [SAFE]: The skill references 'https://picsum.photos' as a source for placeholder background images. This is a well-known and standard utility service for developers and does not pose a security risk in this context.
Audit Metadata