debugging-toolkit-smart-debug
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through its ingestion of external data.
- Ingestion points: Untrusted data enters the agent context via the $ARGUMENTS variable, intended for error logs and issue reports (SKILL.md).
- Boundary markers: The workflow lacks explicit delimiters or markers to isolate untrusted input from system instructions.
- Capability inventory: The skill possesses capabilities to query several observability platforms (e.g., Sentry, DataDog, Splunk) and trigger specialized debugger subagents (SKILL.md).
- Sanitization: There are no documented steps for sanitizing, filtering, or validating the input data before processing.
Audit Metadata