brand-guidelines

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to process external artifacts such as documents, presentations, and websites to apply brand guidelines. This creates an indirect prompt injection surface where malicious instructions embedded within these external materials could potentially influence the agent's behavior.
  • Ingestion points: External organizational materials, documents, and websites referenced in SKILL.md.
  • Boundary markers: None specified to delimit instructions from the content being processed.
  • Capability inventory: The metadata in _meta.json requests access to the exec tool.
  • Sanitization: No sanitization or validation logic is defined for the content being processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 03:23 AM
Security Audit — agent-trust-hub — brand-guidelines