brand-audit
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes external content (websites, ads, social media) to conduct brand audits. This creates a surface for indirect prompt injection if the audited content contains instructions designed to manipulate the agent's assessment.
- Ingestion points: Digital presence (website, social, ads) and marketing materials referenced in SKILL.md.
- Boundary markers: Absent. The instructions do not specify delimiters or warnings to ignore embedded commands within the audited materials.
- Capability inventory: Writing audit reports and matrixes to the local filesystem (.aiwg/marketing/brand/audit/) and orchestrating multiple sub-agents.
- Sanitization: Absent. No mention of filtering or escaping content gathered from external touchpoints.
Audit Metadata