generating-ugc-videos

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted product data and user-supplied text to drive downstream video generation workflows.
  • Ingestion points: Product images and URLs are ingested in Step 1 of SKILL.md, and user-provided claims are ingested in Step 6.
  • Boundary markers: The instructions do not define specific delimiters or instructions to isolate the external product information from the agent's core instructions.
  • Capability inventory: The skill utilizes tools like writing-video-scripts, generating-storyboards, and video_generate which process the ingested data to create final media.
  • Sanitization: There is no explicit evidence of sanitization or validation of the content retrieved from external URLs or user inputs before it is passed to the generation pipeline.
  • [NO_CODE]: The skill consists entirely of markdown instructions and reference files, with no accompanying executable scripts or binaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 05:35 PM
Security Audit — agent-trust-hub — generating-ugc-videos