riscv-mcu-debug
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues detected. The skill's logic is entirely focused on providing technical assistance for embedded systems development using common industry-standard tools.
- [COMMAND_EXECUTION]: The skill provides baseline commands for launching OpenOCD and GDB to interface with microcontrollers. These are diagnostic in nature and are intended to be executed within the user's local development environment.
- [PROMPT_INJECTION]: The skill involves the ingestion and analysis of external data sources such as serial logs and debugger outputs, which constitutes an indirect prompt injection surface. This functionality is essential for the skill's primary purpose of diagnosing firmware issues.
- Ingestion points: The skill requests artifacts including UART logs, trap dumps, and GDB transcripts from the user (SKILL.md).
- Boundary markers: No specific delimiters or warnings for the agent to ignore instructions embedded in the logs are defined.
- Capability inventory: The agent is instructed to use local debugging tools (OpenOCD, GDB) and analyze firmware metadata (ELF, linker scripts).
- Sanitization: There are no explicit instructions to sanitize or validate the content of the diagnostic logs provided by the user.
Audit Metadata