NYC

github-to-skills

Warn

Audited by Snyk on Feb 16, 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). This skill fetches and ingests public GitHub README content via scripts/fetch_github_info.py (using raw.githubusercontent.com and git ls-remote) and the workflow explicitly has the agent analyze the README to plan invocation, exposing it to untrusted user-generated content that could contain indirect prompt injections.

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

  • Potentially malicious external URL detected (high risk: 0.90). The script scripts/fetch_github_info.py performs runtime fetches from raw.githubusercontent.com (e.g., https://raw.githubusercontent.com///main/README.md) and injects the README into the generated SKILL.md and analysis, meaning remote README content can directly influence the agent's prompts/instructions and wrapper generation.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 02:01 AM