load-pr-context

Warn

Audited by Snyk on Feb 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: 0.90). The SKILL.md explicitly instructs the agent to call GitHub MCP APIs (e.g., mcp__github__get_pull_request, list_review_comments, list_pull_request_files) to read PR descriptions, diffs, review comments, and linked issues—all user-generated GitHub content from third-party/public sources that the agent ingests and which can influence its subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 20, 2026, 07:58 AM