The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx @leoflores/datadog-cli to download and execute code from an external NPM package. This package is a community-maintained tool, not an official Datadog release. Use of npx also means code is fetched from the registry at runtime.
[COMMAND_EXECUTION]: The skill performs multiple command line operations, including npx for CLI execution and jq for JSON manipulation of dashboard configurations.
[PROMPT_INJECTION]: The skill is vulnerable to Indirect Prompt Injection (Category 8):
Ingestion points: Data enters the agent via logs search, logs tail, and logs patterns commands (defined in SKILL.md and references/logs-commands.md).
Boundary markers: None identified. The instructions do not define delimiters for log content or warn the agent to ignore instructions within the data.
Capability inventory: The skill has significant capabilities including dashboards update, dashboards delete, and dashboards create (documented in references/dashboards.md).
Sanitization: No evidence of sanitization or validation of log content before it is processed by the agent.

datadog-cli