debug-jlink

Pass

Audited by Gen Agent Trust Hub on May 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/jlink_debugger.py uses subprocess.run and subprocess.Popen to launch the JLinkGDBServer and GDB binaries. These operations are essential for the skill's purpose and are implemented safely using list-based arguments to prevent shell injection.\n- [PROMPT_INJECTION]: The skill has an ingestion surface for indirect prompt injection as it processes external ELF files and executes debugger commands based on user-provided paths. This is a standard and expected pattern for local development and debugging tools.\n
  • Ingestion points: The tool accepts paths to ELF binaries and GDB executables via command-line arguments in scripts/jlink_debugger.py.\n
  • Boundary markers: No explicit boundary markers or "ignore embedded instructions" warnings are used when processing local files.\n
  • Capability inventory: The skill executes local subprocesses (GDB, JLinkGDBServer) and writes temporary GDB scripts to the local file system.\n
  • Sanitization: The script validates file existence using pathlib and uses list-based command execution (avoiding shell=True) to prevent common command injection vectors.
Audit Metadata
Risk Level
SAFE
Analyzed
May 2, 2026, 02:26 PM