lambda-workflow

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill instructs the agent to read and react to GitHub PRs, checks, reviews, and comment streams (via direct GitHub actions and the Dumbwaiter MCP), which are public/user-generated sources and thus untrusted third-party content that the agent must interpret.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 12:45 PM