opening-in-ide

Pass

Audited by Gen Agent Trust Hub on Apr 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local shell and PowerShell scripts to launch IDEs. This is the intended primary purpose and is implemented using standard script-based automation.
  • [DATA_EXFILTRATION]: No network-capable commands (e.g., curl, wget, fetch) or external data transfer mechanisms were found in the scripts or instructions.
  • [EXTERNAL_DOWNLOADS]: The skill does not download any external code, packages, or assets at runtime.
  • [PROMPT_INJECTION]: Instructions are focused on task execution and do not contain patterns attempting to bypass safety filters or override agent constraints.
  • [SAFE]: The Python scripts in the tests and evals directories are for internal validation and do not perform any dangerous operations on the host system beyond creating temporary test files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 17, 2026, 05:06 AM