eval-trace-rca
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs legitimate analysis of production telemetry data using authorized platform tools.
- [DATA_EXFILTRATION]: The skill allows for exporting analysis results to Datadog notebooks via the
create_datadog_notebooktool. This operation maintains data within the vendor's ecosystem and is a standard feature of the intended service. - [PROMPT_INJECTION]: The skill processes untrusted production data from traces (e.g., user prompts and LLM responses), which constitutes an indirect prompt injection surface. This risk is mitigated by the skill's structured analysis workflow and the requirement for user approval before taking any significant actions like modifying code.
Audit Metadata