debugging-toolkit-smart-debug

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an Indirect Prompt Injection surface (Category 8).
  • Ingestion points: The skill ingests untrusted data via the $ARGUMENTS placeholder in the Context section of SKILL.md.
  • Boundary markers: There are no delimiters or explicit instructions to treat the content of $ARGUMENTS as data rather than instructions.
  • Capability inventory: The workflow utilizes a high-privilege Task tool (subagent_type="debugger") capable of deep code analysis and generating fix implementations.
  • Sanitization: The skill lacks sanitization or validation steps for the external input before it is processed by the AI agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 07:48 AM