debug-component
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it processes untrusted data from external sources.
- Ingestion points: Job details (
mcp__keboola__get_job), component configurations (mcp__keboola__get_config), and external logs (Datadog API). - Boundary markers: No explicit markers are defined to help the agent distinguish between its own instructions and untrusted data from logs.
- Capability inventory: The agent can execute shell commands via the
Bashtool, including running local code. - Sanitization: No sanitization is performed on the ingested log or telemetry data.
- [COMMAND_EXECUTION]: The agent uses the
Bashtool to run local code (uv run) and execute tests (pytest). This is necessary for the skill's primary function. - [EXTERNAL_DOWNLOADS]: The skill performs network operations to the Datadog API and uses
uv syncto manage dependencies. These interactions target well-known and trusted services.
Audit Metadata