skills/microsoft/apm/shepherd-driver/Snyk

shepherd-driver

Warn

Audited by Snyk on Jul 15, 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). Yes: the shepherd-driver subagent fetches outsider-authored PR review/comment body text from GitHub (copilot-pull-request-reviewer[bot] reviews/comments) via gh api .../reviews and gh api .../comments, then uses those bodies as LLM-visible copilot_findings/rationale inputs in the convergence loop.

Issues (1)

W011

MEDIUM

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

Audit Metadata

Risk Level

MEDIUM

Analyzed

Jul 15, 2026, 03:36 PM

Issues

1

Security Audit — snyk — shepherd-driver