tubelab-mcp

Fail

Audited by Snyk on Nov 21, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The skill is a legitimate TubeLab data-layer reference, but its instruction to keep credit counts and budgets out of the report while spending paid credits hides the skill's own spending from the user, which is sketchy but not malicious.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (low risk: 0.10). The required workflow calls TubeLab search tools that return outsider-authored YouTube titles and descriptions, and transcript and comment reads for videos the agent selects, so the agent must actively query or fetch this content and an outsider cannot force delivery into a monitored feed.

Issues (2)

E004
CRITICAL

Prompt injection detected in skill instructions.

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 21, 2026, 04:48 PM
Issues
2