datadog-automation

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data from Datadog, which creates a potential surface for indirect prompt injection. A malicious log entry or metric could contain instructions designed to influence the agent's behavior during log analysis or dashboard management.
  • Ingestion points: Tools like DATADOG_SEARCH_LOGS, DATADOG_QUERY_METRICS, and DATADOG_LIST_EVENTS in SKILL.md ingest untrusted external data.
  • Boundary markers: The instructions do not define clear delimiters or specific warnings to ignore embedded instructions within the processed data.
  • Capability inventory: The skill possesses significant capabilities, including the ability to delete dashboards (DATADOG_DELETE_DASHBOARD), update monitors (DATADOG_UPDATE_MONITOR), and schedule downtimes (DATADOG_CREATE_DOWNTIME).
  • Sanitization: There are no explicit requirements for sanitizing or escaping the data retrieved from external sources before further processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 12:54 PM
Security Audit — agent-trust-hub — datadog-automation