review

Warn

Audited by Snyk on Apr 21, 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.md explicitly instructs in "Pass 1: Step 0" to "always fetch" ticket URLs found in PR descriptions (e.g., Jira/Linear/GitHub issue links), meaning the agent will retrieve and interpret user-generated third‑party ticket/webpage content that can directly affect review decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 21, 2026, 08:32 AM
Issues
1