ds-design-audit
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content and has capabilities to modify local project files, creating a surface for indirect prompt injection.
- Ingestion points: The skill accepts an external target file or URL for rendering and auditing (SKILL.md, Step 1).
- Boundary markers: None provided. The instructions do not specify using delimiters or provide warnings to ignore instructions embedded within the target content.
- Capability inventory: The skill uses tools to take screenshots (Step 2/8), reads source code (Step 3), and performs file system writes to apply code fixes (Step 7).
- Sanitization: None provided. The skill does not mention sanitizing or validating the content of the target before processing.
Audit Metadata