memory

Warn

Audited by Snyk on Apr 7, 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 issues GET requests to a configurable mixlab endpoint (GET {MEMORY_API_BASE_URL}/api/agent/v1/memories as shown in SKILL.md and scripts/query.js) to retrieve user-generated "memories" which the agent reads, summarizes, and uses in its workflow, so untrusted third-party content could inject instructions that influence subsequent behavior.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 7, 2026, 07:32 PM
Issues
1