make-ci-green

Warn

Audited by Snyk on May 2, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill fetches and parses live, user-generated CI data (Jenkins build and console output via fetch_console_tail/get_failed_stage and GitHub PR and issue data via gh calls) and uses parsed stage names and test output to decide WIPE_WORKSPACE vs normal reruns and to suggest filing issues, so untrusted third‑party content can directly influence actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 2, 2026, 06:15 PM
Issues
1