youtube-transcript
Warn
Audited by Snyk on Oct 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The skill retrieves YouTube video transcripts via an external API, ingesting outsider-authored video caption text into the agent's context when selected by the user.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (medium risk: 0.30). The skill connects to a hosted third-party MCP endpoint (
https://data.flashdata.dev/mcp) which provides tool execution instructions and runtime behavior, representing a common/reputable unofficial operational dependency.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata