Skills
skills/manojbajaj95/claude-gtm-plugin/youtube-video-analyst/Gen Agent Trust Hub

youtube-video-analyst

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and analyze untrusted external data from YouTube transcripts.
  • Ingestion points: YouTube transcripts are retrieved via scripts/fetch_transcript.py or manually provided by the user.
  • Boundary markers: Absent. The prompt instructions do not specify delimiters to separate the untrusted transcript text from the agent's core instructions.
  • Capability inventory: The skill utilizes scripts/fetch_transcript.py to interact with external YouTube endpoints.
  • Sanitization: Absent. The ingested transcript content is processed directly without filtering or sanitization.
  • [COMMAND_EXECUTION]: The skill provides instructions to execute a local Python script scripts/fetch_transcript.py for fetching data. The script uses secure practices, including argparse for input handling and re for URL validation, which mitigates standard command injection risks.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 08:49 PM