review-pull

Warn

Audited by Snyk on Jun 20, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.85). The skill is “Review Pull Request” and its runtime workflow (e.g., tea pulls review, tea pulls review-comments, tea pulls 15 --fields diff,patch) necessarily ingests PR diff/patch and comment text from the target repository/PR, which is outsider-authored content (other users’ PRs/comments) delivered via the platform’s APIs into the agent’s LLM context.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 20, 2026, 09:18 AM
Issues
1
Security Audit — snyk — review-pull