datadog
Pass
Audited by Gen Agent Trust Hub on Apr 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Provides templates for the agent to execute
curlandjqcommands for interacting with Datadog's observability platform. - [EXTERNAL_DOWNLOADS]: Fetches configuration and data from Datadog's official API domains, which are recognized as well-known and trusted services.
- [PROMPT_INJECTION]: Contains a surface for indirect prompt injection via data retrieved from external sources.
- Ingestion points: Log events, APM traces, and monitor definitions fetched from the Datadog API (SKILL.md).
- Boundary markers: None are defined to separate ingested data from agent instructions.
- Capability inventory: Uses
curlfor network requests andjqfor data processing. - Sanitization: No validation or sanitization is performed on the data returned from the API before it is presented to the agent context.
Audit Metadata