mcp-detector

Warn

Audited by Snyk on Feb 16, 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). This skill recommends and can invoke tools that search and ingest content from public sources—explicitly mcp__plugin_oh_grep_app__searchGitHub (GitHub) and mcp__plugin_oh_web_search__web_search_exa (open web)—so the agent would read untrusted, user-generated third-party content as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:50 AM