skills/openhands/extensions/datadog/Gen Agent Trust Hub

datadog

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides bash commands using curl and jq to interact with Datadog's API. These operations are restricted to the skill's intended purpose of data retrieval and analysis.\n- [PROMPT_INJECTION]: The skill fetches external data (logs and traces) from Datadog, representing a potential indirect prompt injection surface. This is an inherent risk for observability tools that process third-party data.\n
  • Ingestion points: Log and trace data retrieved from Datadog API endpoints in SKILL.md.\n
  • Boundary markers: Not present in the provided instructions.\n
  • Capability inventory: Agent uses standard utilities curl and jq for API interaction.\n
  • Sanitization: No content sanitization is performed on retrieved data.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 01:58 PM
Security Audit — agent-trust-hub — datadog