datadog-logs

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill follows security best practices for integrating with Datadog. It uses environment variables for API and application keys and focuses on read-only log analysis tasks.- [PROMPT_INJECTION]: The skill ingests log data from Datadog, which is a potential surface for indirect prompt injection.
  • Ingestion points: The search_logs and get_log_details tools retrieve log content from the Datadog API.
  • Boundary markers: There are no explicit markers or instructions to treat log content as untrusted data.
  • Capability inventory: The skill only provides read-only log retrieval and configuration listing; it does not have the ability to execute code, write files, or perform network operations outside the Datadog API.
  • Sanitization: Content retrieved from Datadog is not sanitized or filtered for prompt injection patterns before being presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 04:29 PM
Security Audit — agent-trust-hub — datadog-logs