review

Warn

Audited by Snyk on Jul 12, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.75). The workflow fetches outsider-authored issue/PR text via docs/agents/issue-tracker.md (step 2.1) and then includes the fetched spec contents in the Spec sub-agent prompt, so the LLM ingests free-form text authored by external parties at runtime.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 12, 2026, 10:38 PM
Issues
1
Security Audit — snyk — review