debugging-wizard

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to process untrusted external data such as error messages and log entries, creating an indirect prompt injection surface.
  • Ingestion points: Logs and error messages are used as primary input for debugging (SKILL.md).
  • Boundary markers: No specific delimiters are used to separate untrusted inputs from agent instructions.
  • Capability inventory: No tools or automated execution capabilities are defined within the skill files.
  • Sanitization: No sanitization or validation of input data is present.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 01:10 AM