datadog-automation
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it reads potentially attacker-controlled data and possesses destructive capabilities.
- Ingestion points: The agent retrieves untrusted data from external sources via tools such as
DATADOG_SEARCH_LOGS,DATADOG_LIST_EVENTS,DATADOG_LIST_METRICS, andDATADOG_LIST_HOSTS(SKILL.md). - Boundary markers: There are no instructions provided to set boundary markers or to ignore embedded instructions within the data retrieved from Datadog.
- Capability inventory: The skill enables high-impact tools including
DATADOG_DELETE_DASHBOARD,DATADOG_CREATE_MONITOR,DATADOG_UPDATE_MONITOR,DATADOG_MUTE_MONITOR,DATADOG_CREATE_EVENT, andDATADOG_CREATE_DOWNTIME(SKILL.md). - Sanitization: No sanitization, escaping, or validation logic is defined for the external data before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill references and requires the use of external infrastructure.
- The setup instructions direct the user to add
https://rube.app/mcpas an MCP server (SKILL.md). - The skill links to external documentation and toolkit information at
https://composio.dev/toolkits/datadog(SKILL.md).
Audit Metadata