youtube-research-video-topic
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill makes use of specialized YouTube analytics tools (
mcp__plugin_yt-content-strategist_youtube-analytics) which are consistent with the developer's purpose and namespace. No unauthorized command execution or sensitive file access was detected. - [PROMPT_INJECTION]: The skill processes untrusted data from YouTube metadata and web search results, which is a common surface for indirect prompt injection. However, given the skill's purpose for document synthesis and the lack of dangerous downstream capabilities, the risk is negligible.
- Ingestion points: External content fetched via
mcp__plugin_yt-content-strategist_youtube-analytics__search_videosandweb-fetch. - Boundary markers: None defined to isolate external data from instructions.
- Capability inventory: Filesystem write permissions for research report generation.
- Sanitization: No explicit content filtering or validation of external data is performed before processing.
Audit Metadata