error-diagnostics-smart-debug
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- Indirect Prompt Injection (LOW): The skill is designed to process untrusted data from external observability sources which may contain malicious instructions. \n
- Ingestion points: The
$ARGUMENTSvariable and data retrieved from external platforms like Sentry, DataDog, and Splunk. \n - Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore' instructions for the interpolated data. \n
- Capability inventory: The workflow utilizes a 'debugger' subagent with capabilities including code flow reconstruction, fix generation, and test suite execution. \n
- Sanitization: No sanitization or validation of external input is specified in the workflow instructions.
Audit Metadata