advertising-video-production
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface through the ingestion and processing of external campaign briefs and product data. \n
- Ingestion points: Relies on external project briefs, brand evidence, and research sources as described in
SKILL.md. \n - Boundary markers: The instructions do not specify the use of XML tags or other delimiters to isolate untrusted brief content. \n
- Capability inventory: The agent is instructed to perform file operations (ledger recording), media probing (output inspection), and local rendering as part of the production workflow. \n
- Sanitization: The skill mandates rigorous factual verification and manual inspection of representative frames to ensure outputs align with the truthful product evidence.
Audit Metadata