review-design
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions involve processing external data sources which represents a potential attack surface.
- Ingestion points: Analyzes project design documentation (e.g., docs/frontend/DESIGN.md) and code diffs as specified in the Scope section of SKILL.md.
- Boundary markers: The instructions do not specify the use of clear delimiters or isolation markers when the agent processes these external files.
- Capability inventory: The skill is strictly limited to generating textual feedback in a Markdown table format. It explicitly prohibits editing code or refactoring, and contains no instructions for subprocess calls, file writes, or network access.
- Sanitization: No explicit sanitization or validation of the input file content is defined.
- [NO_CODE]: The skill is composed entirely of Markdown instructions and does not include any scripts or executable code.
- [SAFE]: The skill's behavior is restricted to 'findings only,' effectively preventing any side effects or unauthorized modifications to the environment.
Audit Metadata