The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, which can lead to indirect prompt injection if those sources contain malicious instructions.
Ingestion points: The skill ingests data from DATADOG_SEARCH_LOGS, DATADOG_LIST_EVENTS, and DATADOG_GET_TRACE_BY_ID (SKILL.md).
Boundary markers: Absent. There are no instructions or delimiters defined to prevent the agent from following instructions embedded within the logs or events it retrieves.
Capability inventory: The skill provides access to several high-impact tools, including DATADOG_DELETE_DASHBOARD, DATADOG_CREATE_MONITOR, and DATADOG_UPDATE_DASHBOARD.
Sanitization: Absent. No evidence of escaping or validation of retrieved data is provided.
[EXTERNAL_DOWNLOADS]: The skill instructs users to connect to a third-party MCP server at https://rube.app/mcp. This external service acts as an intermediary for sensitive Datadog infrastructure and observability data and is not categorized as a well-known or trusted service.

datadog-automation