youtube-own-channel-analyzer
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill interacts with the official YouTube Data API at
https://www.googleapis.com/youtube/v3to retrieve channel statistics and video metadata. This interaction targets a well-known and trusted service. - [PROMPT_INJECTION]: The skill processes untrusted external data (YouTube video titles and descriptions) during its analysis workflow, which could theoretically be used for indirect prompt injection.
- Ingestion points: Video snippets (title, description) fetched via the
/videosand/searchendpoints as described in SKILL.md. - Boundary markers: The instructions do not define specific delimiters or warning prompts to isolate external data from agent instructions.
- Capability inventory: The agent is instructed to perform network operations (HTTP GET) to the YouTube API and generate textual reports.
- Sanitization: There are no explicit instructions for filtering or sanitizing the content retrieved from the API before it is processed for analysis.
Audit Metadata