unify-design
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted source code, components, and git history from the user's project to identify design drift. Maliciously crafted content in these files, such as instructions hidden in code comments or metadata, could attempt to influence the agent's behavior during the audit process.
- Ingestion points: Source code files (src/, app/, components/, pages/) and git logs analyzed via glob and grep tools.
- Boundary markers: The skill uses specific regex patterns for design values but lacks explicit delimiters or instructions to ignore embedded natural language commands in the analyzed files.
- Capability inventory: The skill has the ability to modify files (Write/Edit) and execute shell commands (git, npm).
- Sanitization: No specific sanitization or escaping of the ingested code content is defined before the agent processes it for classification.
Audit Metadata