pr-issue-resolve

Warn

Audited by Snyk on Mar 1, 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). This skill explicitly instructs the agent to fetch and interpret user-generated GitHub PR content (e.g., via "gh pr view" and "gh pr comment list" in SKILL.md), which the agent will read and act on (apply suggested diffs, change code, respond), exposing it to untrusted third-party input that could carry indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 01:37 AM