openclaw-youtube
Warn
Audited by Snyk on Feb 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). This skill calls the public YouTube search API via the AIsa endpoint (see scripts/youtube_client.py which requests https://api.aisa.one/apis/v1/youtube/search) and ingests user-generated titles, descriptions and metadata that the agent reads and analyzes for content research, exposing it to untrusted third-party input that could enable indirect prompt injection.
Audit Metadata