clip-opportunity-analyzer
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill retrieves metadata and transcripts from major video platforms including YouTube, TikTok, Twitch, and Instagram using the
web_fetchtool. These are well-known services used for the skill's primary analytical purpose. - [SAFE]: The skill processes untrusted external data (transcripts), which represents a surface for indirect prompt injection. The risk is mitigated by the structured workflow and scoring dimensions defined in the instructions.
- Ingestion points: External transcripts fetched from user-provided URLs as described in SKILL.md.
- Boundary markers: No specific delimiters are defined for the fetched transcript text.
- Capability inventory: Uses
web_fetchfor data retrieval; no dangerous command execution tools are invoked on the fetched data. - Sanitization: No explicit text sanitization or filtering is implemented for the transcript content.
Audit Metadata