youtube-export

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a command-line interface (yt-insights) to export transcript data. It passes user-provided parameters like video identifiers and formats directly to the CLI tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external transcript data which could theoretically contain malicious instructions aimed at downstream processing.
  • Ingestion points: Video transcripts are read from the yt-insights corpus as described in SKILL.md.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded content within the exported text content.
  • Capability inventory: The skill executes the yt-insights CLI command and can perform file system writes (with user authorization for overwrites).
  • Sanitization: No content-level sanitization or filtering is performed on the transcript data before it is returned or saved.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 04:54 PM
Security Audit — agent-trust-hub — youtube-export