openocd-jtag
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The instructions and examples provided are typical for embedded systems development and debugging workflows. The shell commands and TCL configurations match the stated purpose of the skill.
- [COMMAND_EXECUTION]: The skill provides standard command-line snippets for interacting with local development tools (e.g.,
openocd,arm-none-eabi-gdb,telnet). These are used to control hardware debuggers and flash firmware to microcontrollers. - [INDIRECT_PROMPT_INJECTION]: The skill involves the agent interacting with external firmware files (
.elf,.bin). - Ingestion points: The agent processes firmware binaries via flashing commands (e.g.,
program firmware.elf). - Boundary markers: None present; the firmware is treated as binary data for hardware operations.
- Capability inventory: Shell execution of debugger tools and network connection to local ports (3333/4444).
- Sanitization: Not applicable as the content is binary firmware intended for hardware execution, not natural language processing by the agent.
Audit Metadata