closed-loop

Warn

Audited by Snyk on Aug 26, 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 skill’s runtime workflow ingests outsider-authored free text via the opt-in /closed-loop <task> (or spec-path) argument that is passed into lane classification and then drives the plan/verification steps.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 26, 2026, 11:34 AM
Issues
1
Security Audit — snyk — closed-loop