logs-nodejs
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and analysis of application logs by AI agents via an MCP server integration. Because logs are external, untrusted data sources, they could contain malicious instructions designed to influence agent behavior.\n
- Ingestion points: The
logs-querytool described inreferences/debug-logs-mcp.mdenables the agent to retrieve and process log content.\n - Boundary markers: The documentation does not specify explicit boundary markers or instructions to treat log content as untrusted data.\n
- Capability inventory: The agent is provided with tools to query logs, list attributes, and inspect attribute values.\n
- Sanitization: The documentation does not detail any sanitization or filtering processes for log data before it reaches the agent context.\n- [EXTERNAL_DOWNLOADS]: The documentation in
references/nodejs.mdinstructs users to install standard observability packages from the@opentelemetryorganization via NPM. These are well-known, trusted packages within the developer ecosystem.
Audit Metadata