The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted log data from Datadog via search tools, creating a surface for indirect instructions to be processed by the agent. * Ingestion points: outputs from search_logs and get_log_details tools in SKILL.md. * Boundary markers: None; no instructions provided to treat log data as untrusted or to use delimiters. * Capability inventory: Limited to log searching and reading; no file-system or network-writing tools are included in the skill. * Sanitization: None; no logic exists to escape or validate external log content.
[NO_CODE]: This skill contains no executable scripts or local code; it only provides instructions and documentation for interacting with the datadog-mcp server.

datadog-logs