product-video-ad-skill
Pass
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data such as product URLs and descriptions, creating a surface for indirect prompt injection where external content could influence agent behavior.
- Ingestion points: Data enters through product URLs and user descriptions defined in SKILL.md.
- Boundary markers: Absent; the skill lacks delimiters or 'ignore' instructions for external content.
- Capability inventory: The skill contains prompt instructions only and no code execution capabilities.
- Sanitization: Absent; no validation is performed on retrieved external content.
Audit Metadata