agency-design-system

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests untrusted content from project files, creating a surface for indirect prompt injection. This is assessed as safe because the skill's capabilities are restricted and its output is limited to design documentation.
  • Ingestion points: copy.md and .agency/context/visual-identity.md.
  • Boundary markers: None identified in the provided instructions.
  • Capability inventory: The skill is restricted to read-only file system tools (Read, Grep, Glob).
  • Sanitization: No explicit sanitization or validation of ingested text is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 06:35 PM