normalize
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from the repository (design documentation, UI guides, and style guides) which could be manipulated to deliver malicious instructions to the agent.
- Ingestion points: The skill uses file searches and reads for strings such as "design system", "ui guide", and "style guide" to gather context for normalization in SKILL.md.
- Boundary markers: There are no defined delimiters or instructions to treat the content of discovered documentation as data only, lacking protection against embedded instructions.
- Capability inventory: The skill is authorized to perform file system read/write operations and execute shell commands for linting, type-checking, and running tests.
- Sanitization: No sanitization, filtering, or validation is performed on the content of the design documentation or the code being refactored before it is processed by the agent.
Audit Metadata