youtube-channel-deep-analysis
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands to run a local Python automation script (
..\_shared\scripts\youtube_growth_automation.py) for data collection, summarization, and HTML report generation. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data from YouTube, such as transcripts, titles, and descriptions, which could contain instructions intended to influence the agent's behavior.
- Ingestion points: The agent reads content from generated JSON files like
channel-sample.jsonandchannel-recent.jsonas specified inSKILL.md. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the YouTube metadata or transcripts.
- Capability inventory: The skill allows the agent to execute shell commands (via the Python script) and write output to the filesystem in JSON and HTML formats.
- Sanitization: There is no evidence of sanitization or filtering of the external YouTube content before it is processed by the agent during the deep strategy analysis phase.
Audit Metadata