create-readme

Warn

Audited by Snyk on Feb 25, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to "take inspiration" from four raw.githubusercontent.com URLs (public GitHub raw files), which requires fetching and interpreting untrusted, user-published content that could influence the agent's output and behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 25, 2026, 05:26 AM