runaway-stopper

Warn

Audited by Snyk on Nov 16, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.30). The required Step 1 program reads crew thread transcripts via tools.thread.get, and it passes wait tool inputs through unfiltered. Those transcripts can contain text from GitHub PRs and issues that the threads read, and the agent gets this data without selecting any specific item, so the risk is medium under the recall-first rule.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 16, 2026, 08:17 PM
Issues
1