ai-testimonial-video
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided text and image URLs to generate AI video content, creating a surface where untrusted data could influence model behavior.
- Ingestion points: The
contentfield within themessagesarray in the API request examples (SKILL.md). - Boundary markers: No explicit delimiters or 'ignore instructions' guards are implemented for the user-supplied prompts.
- Capability inventory: The skill uses
Bash(curl)and theopenaiPython SDK for network-based API communication (SKILL.md). - Sanitization: No input validation or filtering of external content is specified before the data is sent to the remote API.
Audit Metadata