character-animation-qa
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources, creating a surface for indirect instructions.
- Ingestion points: The agent visits external URLs via Playwright and probes MP4 files.
- Capability inventory: The skill utilizes shell commands through FFmpeg and ffprobe, along with browser automation.
- Boundary markers: No delimiters or instructions are provided to the agent to ignore content in the reviewed media.
- Sanitization: There is no specification for sanitizing external metadata or web content.
- [COMMAND_EXECUTION]: The skill employs FFmpeg and ffprobe for probing media files and sampling frames for visual analysis.
- [EXTERNAL_DOWNLOADS]: The skill includes links to official documentation for Playwright and FFmpeg, which are trusted technology providers.
Audit Metadata