pr-review

Warn

Audited by Snyk on Mar 18, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and ingests untrusted, user-generated content—PR diffs, PR titles/descriptions, commit messages via gh pr view/gh pr diff and git in _review-core.md, and JIRA tickets/comments via mcp__atlassian__getJiraIssue in agents/jira-completeness.md—and uses that content to drive reviews, spawn sub-agents, and adjust verdicts, so third-party content can materially influence agent actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 18, 2026, 11:21 AM
Issues
1