code-reviewer

Warn

Audited by Snyk on Mar 6, 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 Remote PR workflow in SKILL.md instructs the agent to checkout GitHub PRs and read the PR description and comments, which are untrusted, user-generated content from public GitHub that the agent will interpret and use to guide review actions, enabling indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 6, 2026, 11:11 AM