circuit-debugger
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill content consists of educational documentation and bundled scripts for hardware debugging, which is consistent with its stated purpose.
- [COMMAND_EXECUTION]: The skill instructions provide examples for using 'uv run' to execute a local Python script, 'scripts/generate_debug_sketch.py'. This is a standard method for utilizing local tools within the agent environment.
- [DYNAMIC_EXECUTION]: The generation script creates Arduino source code by interpolating user-provided inputs into code templates. The generated scripts are written to local files for use with microcontrollers, and the process does not involve untrusted remote sources.
- [INDIRECT_PROMPT_INJECTION]: There is a potential attack surface for indirect prompt injection via the command-line arguments of the generation script (e.g., custom pin names). However, because the output is C++ code for embedded targets, there is no direct risk to the host system or the agent's logic.
- [METADATA_POISONING]: The skill metadata, including the name, description, and tags, accurately describes the functionality and does not contain deceptive instructions or hidden behavior.
Audit Metadata