acquire

Warn

Audited by Snyk on Mar 4, 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). The SKILL.md explicitly shows the agent listing and reading Acquire data (e.g., "List Messages", "Get Case") and allows proxying arbitrary API endpoints via "membrane request CONNECTION_ID /path/to/endpoint", which ingests user-generated third-party chat/content that could contain instructions influencing subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 08:56 AM