The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill uses npx to download and execute the @leoflores/datadog-cli package from the NPM registry at runtime. This package is an unverified third-party dependency provided by a non-trusted source.- [EXTERNAL_DOWNLOADS]: The skill facilitates the download of external code from the NPM registry via npx and references an external GitHub repository leonardocouy/datadog-cli for the CLI tool's documentation and source.- [COMMAND_EXECUTION]: The skill's core functionality relies on executing shell commands, including npx to run the Datadog CLI and jq to parse and manipulate JSON data stored in temporary files (e.g., /tmp/dashboard.json).- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes external, untrusted data from Datadog logs and dashboard configurations. Ingestion points: Untrusted data is retrieved from Datadog via logs search, logs tail, and dashboards get commands. Boundary markers: There are no explicit instructions or delimiters provided to the agent to distinguish between its own instructions and instructions potentially embedded in the retrieved Datadog data. Capability inventory: The agent has the capability to execute shell commands (npx, jq, cat) and write files to the local system. Sanitization: There is no evidence of sanitization or validation of the content fetched from Datadog before it is processed by the agent.

datadog-cli