learn

Warn

Audited by Snyk on Oct 30, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (low risk: 0.10). The skill reads public content from ratstack.sh via curl and MCP tools, which is a low-risk active fetch of external URLs and public decks rather than an unprompted monitored feed.

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

  • Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to clone a repository from GitHub (https://github.com/joelhooks/rat-stack.git) and build and run code from it, constituting a weak/unknown external operational dependency.

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
Oct 30, 2026, 01:30 PM
Issues
2