datadog
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and displays observability data from external Datadog sources which are considered untrusted. This data could contain malicious prompts designed to manipulate the agent's behavior.
- Ingestion points: The search-logs, search-spans, list-monitors, and list-incidents commands in scripts/datadog.ts fetch data from the external Datadog API.
- Boundary markers: The skill does not implement delimiters or isolation instructions to separate external data from the agent's core instructions.
- Capability inventory: The skill has network capabilities to interact with the Datadog API but lacks local file system write or command execution permissions.
- Sanitization: No sanitization, filtering, or validation is performed on the retrieved observability data before it is presented to the agent's context.
Audit Metadata