datadog
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional and guides the agent on how to use Datadog MCP tools to query telemetry data (logs, metrics, traces) for the 'Gram' project. No malicious patterns or security risks were identified in the instructions.\n- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by ingesting data from external telemetry sources.\n
- Ingestion points: External logs, spans, and incident data are brought into the agent context via tools like
mcp__datadog-mcp__search_datadog_logsandmcp__datadog-mcp__search_datadog_incidents(SKILL.md).\n - Boundary markers: The skill does not define specific delimiters or instructions to the agent to disregard potential commands embedded within the retrieved telemetry data.\n
- Capability inventory: The skill does not define or request capabilities for local file-system access, arbitrary subprocess execution, or raw network operations.\n
- Sanitization: No sanitization or validation logic for the content retrieved from external tools is specified in the skill.
Audit Metadata