self-integration

Warn

Audited by Snyk on Feb 19, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill explicitly connects to external apps (e.g., Slack, GitHub) via Membrane and its workflow (Step 2 GET /actions and Step 3 POST /actions/{actionId}/run) returns and requires interpreting an action's "output" from those third-party sources, so untrusted/user-generated content can be ingested and materially influence subsequent agent actions.

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

  • Potentially malicious external URL detected (high risk: 1.00). The skill makes runtime API calls to the Membrane agent endpoint (https://api.getmembrane.com) to create agent sessions that receive prompts and build connectors/actions (i.e., execute remote agent code), and the skill depends on that service for core functionality.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 19, 2026, 11:23 PM