dt-obs-ext-monitors

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE]: The skill provides instructions for sending monitoring data to external Dynatrace platform endpoints (e.g., https://{env-id}.live.dynatrace.com/platform/ingest/custom/events/external.tests). This is legitimate functionality for the Dynatrace observability platform.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for ingesting external data (test results, error messages, URLs) into the Dynatrace Grail database.
  • Ingestion points: Data enters the system via the platform events ingest API as described in SKILL.md and references/event-ingestion.md.
  • Boundary markers: The skill specifies a rigid JSON schema for events, which acts as a structural boundary.
  • Capability inventory: The skill uses DQL (Dynatrace Query Language) for data analysis; it does not involve subprocess execution, remote code, or file system modifications on the agent's host.
  • Sanitization: The documentation states that the ingestion pipeline automatically masks sensitive query parameters in URLs, such as token, api_key, password, and secret.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 03:44 PM
Security Audit — agent-trust-hub — dt-obs-ext-monitors