github

Warn

Audited by Snyk on Oct 12, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.30). The GitHub skill integrates with GitHub via Membrane, allowing the agent to read issues, pull requests, and repository content which can contain outsider-authored text.

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

  • Potentially malicious external URL detected (high risk: 0.70). The skill instructs the installation and execution of an arbitrary npm package (@membranehq/cli) from an unverified third-party vendor without independent cryptographic verification, constituting a weak 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 12, 2026, 04:54 PM
Issues
2