ralph-enhance
Fail
Audited by Snyk on Feb 16, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E006: Malicious code pattern detected in skill scripts.
- Malicious code pattern detected (high risk: 1.00). This skill is high-risk: it mandates autonomous execution of shell commands that read/copy user home files, download external scripts, modify code/DB, run tests and commit changes without further consent—behaviors that enable unauthorized data access, supply-chain modification, and remote code execution.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly reads and interprets user-provided URL(s) and other documents (Step 1.1/1.2) and also downloads templates directly from raw.githubusercontent.com (Step 2.4), meaning it ingests open/public third‑party content that can be untrusted and influence the agent's behavior.
Audit Metadata