brand-guidelines
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to ingest content from external websites and social media profiles to automatically draft brand guidelines, which creates a surface for indirect prompt injection.
- Ingestion points: Instructions in
SKILL.mddirect the agent to study the site, social profiles, and packaging photos. - Boundary markers: No delimiters or safety instructions are defined to distinguish between data and potential malicious instructions in external content.
- Capability inventory: The agent is instructed to write structured guidelines to the
.agents/brand-guidelines.mdfile. - Sanitization: No explicit sanitization or validation of the ingested external content is required before processing.
Audit Metadata