youtube-channels

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: HIGHCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
  • Persistence Mechanisms (HIGH): The skill documentation states that the tapi-auth.js script saves the API key to the user's shell profile (e.g., .bashrc or .zshrc). Modifying shell profiles is a persistence technique used to maintain access and ensure code runs in future sessions.
  • Remote Code Execution (HIGH): The skill instructs the agent to execute a local script ./scripts/tapi-auth.js via node. This script is not provided in the skill package, making its behavior unverifiable and presenting a significant security risk.
  • Command Execution (MEDIUM): The skill makes extensive use of node and curl for authentication and interacting with the YouTube API.
  • Indirect Prompt Injection (LOW): The skill ingests untrusted YouTube metadata which could contain malicious instructions. Evidence: 1. Ingestion points: Video titles and descriptions from channel/latest, channel/videos, and channel/search. 2. Boundary markers: Absent. 3. Capability inventory: Shell command execution (node, curl). 4. Sanitization: Absent.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 17, 2026, 06:07 PM