sitespeakai

Warn

Audited by Snyk on Apr 21, 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 instructs the agent to call arbitrary SiteSpeakAI endpoints (via the "Proxy requests" / membrane request CONNECTION_ID /path/to/endpoint and "Running actions" / membrane action run commands in SKILL.md) and thus can ingest untrusted, user-generated website/chatbot/training data from a third-party API that could influence subsequent actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 21, 2026, 07:44 PM
Issues
1