slack

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 Slack skill enables reading outsider-authored messages and conversations from channels, which are monitored sources.

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 external CLI tool (@membranehq/cli) via npm/npx without an enforced integrity digest or immutable identifier, constituting an unverifiable runtime 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