character-animation-qa
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from external web sources and media file metadata, which can be a vector for indirect prompt injection attacks.
- Ingestion points: External web content via Playwright navigation (
page.goto(previewUrl)) and media metadata throughffprobe(SKILL.md). - Boundary markers: The instructions lack explicit delimiters or safety prompts to prevent the agent from following instructions embedded within the processed media or web content.
- Capability inventory: The skill utilizes browser automation (Playwright) and command-line execution for media probing (
ffprobe). - Sanitization: There is no evidence of validation or sanitization of the input URLs or the data returned from the media analysis tools.
Audit Metadata