seek-and-analyze-video
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The analyzed skill consists only of a markdown documentation file (SKILL.md) which outlines workflows for video analysis. It contains no executable code, scripts, or automated network commands.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to process untrusted external data from sources like YouTube, TikTok, and Instagram, which creates a surface for indirect prompt injection.
- Ingestion points: The skill ingests external content via public video URLs and recording uploads as described in the 'Examples' and 'When to Use' sections of SKILL.md.
- Boundary markers: No explicit boundary markers or 'ignore' instructions for embedded content are defined in the documentation.
- Capability inventory: The skill describes capabilities for video analysis (
chat_video,caption_video), searching within audio (search_audio), and storing results in memory (memory_add) in SKILL.md. - Sanitization: No sanitization or validation methods for the ingested video metadata or transcripts are mentioned in the guide.
Audit Metadata