youtube-own-channel-analyzer
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the YouTube Data API and asks the agent to generate a summary report based on it.
- Ingestion points: Video titles, descriptions, and tags are fetched from YouTube by the bundled script and stored in JSON files in the reports/data/ directory.
- Boundary markers: Step 5 of the instructions directs the agent to write a report based on the data without providing delimiters or explicit instructions to ignore potentially malicious text embedded within the metadata.
- Capability inventory: The skill writes analysis results to the local file system and makes HTTPS requests to official Google API endpoints.
- Sanitization: There is no evidence of content filtering or sanitization applied to the data retrieved from YouTube before it is consumed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the google-api-python-client library.
- Evidence: The skill relies on this well-known and official library from a trusted organization to facilitate communication with YouTube services.
Audit Metadata