debug-mode
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local setup and cleanup scripts (start-collector.mjs, clear-logs.mjs) using the bun runtime and performs health checks on a local service via curl at 127.0.0.1.
- [PROMPT_INJECTION]: The skill processes user input via the $ARGUMENTS variable to inform code instrumentation and hypothesis generation. Ingestion point: $ARGUMENTS field in SKILL.md. Boundary markers: Provided via the ## Bug Description header. Capability inventory: Executes local scripts via bun and modifies user source files. Sanitization: Includes explicit negative constraints instructing the agent to never log sensitive data such as credentials or personal information.
Audit Metadata