ecosystem-guide

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: 0.70). The SKILL.md explicitly instructs enabling "mcp-omnisearch" in the "Research Mode" workflow (e.g., "mcpick enable omnisearch" — "Now Claude has web search, GitHub search, AI answers"), which exposes the agent to open/public web and user-generated sources whose content the agent would read and could materially influence its actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 28, 2026, 08:21 PM