youtube-summarizer

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill automates the installation of the youtube-transcript-api package from the Python Package Index (PyPI). This is a well-known and standard library required for the skill's primary functionality of fetching video transcripts.
  • [COMMAND_EXECUTION]: The skill utilizes shell and Python scripts (scripts/install-dependencies.sh and scripts/extract-transcript.py) to manage its environment and retrieve data. These executions are scoped to the intended purpose of the tool.
  • [DATA_EXFILTRATION]: The skill accesses YouTube's official transcript services via the youtube-transcript-api library. No unauthorized network requests or attempts to send sensitive local data to external servers were identified.
  • [PROMPT_INJECTION]: The skill ingests untrusted content from YouTube transcripts for summarization, which represents a potential indirect prompt injection surface. However, the instructions provide a robust STAR + R-I-S-E framework to guide the AI, and no evidence of adversarial behavior or bypass instructions was found in the skill's code.
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 02:51 AM
Security Audit — agent-trust-hub — youtube-summarizer