memory-research

Warn

Audited by Snyk on Feb 28, 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's SKILL.md (Step 1: "Web Research" and the Guidelines stating "Always web search" and "Store source URLs") explicitly requires performing web searches and ingesting public website/news URLs, so the agent will fetch and interpret untrusted third-party web content to form summaries and drive creation/updates of memory entities.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 28, 2026, 07:57 PM