datadog-automation
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references an external MCP server endpoint at
https://rube.app/mcp. This service is used to provide the underlying tool functionality for the Datadog integration. - [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it retrieves and processes data from external Datadog sources (such as log entries, monitor messages, and event text) which could contain adversarial content.
- Ingestion points: Untrusted data enters the agent context through tools such as
DATADOG_SEARCH_LOGS,DATADOG_LIST_EVENTS, andDATADOG_GET_MONITOR(found in SKILL.md). - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat retrieved data as untrusted or to ignore embedded instructions.
- Capability inventory: The skill has extensive capabilities, including creating, updating, and deleting monitors and dashboards, and posting events (found in SKILL.md).
- Sanitization: No evidence of sanitization or validation of the retrieved content is present in the skill instructions.
Audit Metadata