design-brief
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from project context and external Figma links to generate design briefs. Malicious instructions embedded in these sources could potentially influence the agent's output. The skill possesses file-write capabilities, specifically creating markdown files in a local
briefs/directory, which provides an attack surface for this vector, though the impact is restricted to the generated document's content.
Audit Metadata