The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses local shell commands such as uv run, uv sync, and uv run pytest to execute, synchronize dependencies, and test Python components during the debugging process.
[EXTERNAL_DOWNLOADS]: The skill references and documents the use of Datadog APIs (api.datadoghq.eu and api.datadoghq.com) for log retrieval and analysis. Datadog is a recognized well-known service, and its use is consistent with the skill's purpose.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection due to its core function of processing external data.
Ingestion points: The agent reads job details, configurations, and stack traces via Keboola MCP tools (get_job, get_config), queries Datadog logs, and analyzes local component code.
Boundary markers: There are no explicit instructions or delimiters provided to protect the agent from malicious instructions that might be embedded within the logs or configuration files it processes.
Capability inventory: The agent can execute shell commands (uv run), perform network requests (curl), and trigger platform jobs (run_job).
Sanitization: No specific sanitization or filtering of input data is mentioned before it is processed by the agent.

debug-component