review-work

Warn

Audited by Snyk on Aug 9, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.30). The runtime path described in SKILL.md launches a 5-agent review where the oracle lanes are given full outsider-authored free text from the user’s provided PR/branch context (DIFF + FILE_CONTENTS + conversation GOAL/CONSTRAINTS/BACKGROUND are inserted into the agents’ prompts), and the unspecific-high Context Mining lane may also search communication channels and GitHub issues/PRs for additional outsider-authored text.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 9, 2026, 12:43 PM
Issues
1
Security Audit — snyk — review-work