security-detections-mcp

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to download security detection rules and MITRE ATT&CK STIX data from established and well-known public repositories including SigmaHQ, Splunk, Elastic, and MITRE.
  • [REMOTE_CODE_EXECUTION]: The installation process involves executing code via npx (e.g., npx -y security-detections-mcp), which is a standard distribution method for MCP servers. It also supports connecting to a hosted API endpoint (detect.michaelhaag.org) for remote tool invocation.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests and processes external detection rules (YAML, TOML, JSON) from third-party repositories. However, because these sources are highly reputable cybersecurity projects (MITRE, SigmaHQ), the risk is considered negligible in this context.
  • [CREDENTIALS_UNSAFE]: The skill requires an authorization token for the hosted version, but follows safe practices by instructing users to use environment variables ($SDMCP_TOKEN) rather than hardcoding secrets.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 10:43 PM
Security Audit — agent-trust-hub — security-detections-mcp