synthesis

Warn

Audited by Snyk on May 7, 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 explicitly calls VCS MCP actions that read PRs, reviews, and comments from the VCS provider (e.g., references/synthesis-steps.md Step 4 "check_coderabbit" which queries PR reviews, use of exarchos_orchestrate({ action: "list_prs" }), and the troubleshooting note that "Shepherd reads PR comments"), so it ingests untrusted user-generated PR/review/comment content that can directly change routing and merge decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 7, 2026, 04:36 AM
Issues
1