frontend-design
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill instructs the agent to read and follow design rules from external documentation files ('docs/design.md' and 'docs/sales.md'). This introduces a surface for indirect prompt injection where malicious instructions embedded in those files could potentially influence the agent's behavior or code generation.
- Ingestion points: Documentation is read from 'docs/design.md' and 'docs/sales.md' to guide styling and brand tone.
- Boundary markers: The skill does not provide clear delimiters or instructions for the agent to treat the documentation content as untrusted data rather than instructions.
- Capability inventory: This skill is purely instructional and does not utilize subprocesses, file-writing, or network operations.
- Sanitization: No validation or filtering is applied to the content of the documentation files before it is processed by the agent.
Audit Metadata