pr-testing

Warn

Audited by Snyk on May 5, 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 reads PR comments via gh pr view to extract the "Dogfood this PR" curl/powershell command and then runs scripts fetched from raw.githubusercontent.com (as shown in the SKILL.md install steps), meaning untrusted, user-generated PR comment content and remote repository-hosted scripts are ingested and directly drive installation and execution.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

Issues (2)

W011
MEDIUM

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

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 5, 2026, 06:33 PM
Issues
2