youtube-transcript

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a Bash tool to execute yt-dlp with a user-provided URL to extract subtitles. If the execution environment does not properly sanitize the URL argument, it could potentially be exploited for command injection.
  • [EXTERNAL_DOWNLOADS]: The skill downloads subtitle data from YouTube and requires the installation of the third-party yt-dlp utility.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted transcript data which may contain instructions intended to manipulate the agent's behavior.
  • Ingestion points: Transcript files in .vtt or .srt format are downloaded via yt-dlp and read into the context as described in SKILL.md.
  • Boundary markers: No specific delimiters or instructions are used to treat the transcript content as untrusted data.
  • Capability inventory: The skill has access to shell execution via the Bash tool and file system access via the Write tool.
  • Sanitization: The skill does not perform any sanitization or validation on the transcript content before transforming it into the final note.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 07:53 PM
Security Audit — agent-trust-hub — youtube-transcript