youtube-summarizer

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill identifies a missing dependency and offers to install 'youtube-transcript-api' via pip. This is a well-known package required for the skill's functionality.
  • [COMMAND_EXECUTION]: The skill executes shell commands for environment setup, dependency management, and running the transcript extraction script ('scripts/extract-transcript.py').
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8c) because it processes untrusted transcript data from YouTube videos. 1. Ingestion points: 'scripts/extract-transcript.py' fetches captions via the YouTube API. 2. Boundary markers: 'SKILL.md' contains instructions to treat the transcript as untrusted source material, though no specific delimiters are enforced in the prompt. 3. Capability inventory: The skill has the capability to run shell commands and scripts. 4. Sanitization: No explicit validation or filtering is applied to the transcript content before it is summarized.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 08:37 PM
Security Audit — agent-trust-hub — youtube-summarizer