The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use local shell commands for component setup and testing, specifically utilizing uv sync to manage dependencies and uv run to execute Python scripts and pytest. It also suggests the use of docker for running components in isolated environments.
[EXTERNAL_DOWNLOADS]: To aid in logging analysis, the skill provides curl command examples that interact with the Datadog API (api.datadoghq.eu). Additionally, the uv sync process involves downloading Python packages from standard external registries.
[PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection because it is designed to ingest and analyze untrusted external data.
Ingestion points: The agent reads component source code (src/component.py), external application logs from Datadog, and operational telemetry from Keboola Snowflake databases.
Boundary markers: There are no explicit instructions to use delimiters or 'ignore' commands when processing these external data sources.
Capability inventory: The skill has access to shell command execution (Bash), file system reading, and remote job execution via Keboola MCP tools.
Sanitization: No sanitization or validation protocols are defined for the content retrieved from external sources before it is processed by the agent.

debug-component