isaac-sim-validator
Warn
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: MEDIUMREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The shell script
scripts/validate_sim.shexecutes a Python script path provided as a command-line argument using thepython3interpreter when--level 3is selected. This allows for the execution of arbitrary code with the current user's privileges. - [COMMAND_EXECUTION]: The validator script uses several shell commands (
python3,grep,timeout,find) to analyze and execute local files. It usesreadlink -fto canonicalize paths, which helps prevent basic path traversal, but the tool's core functionality remains the execution of external files. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted script files from other agents or local sources, creating a vulnerability surface where malicious content within those files could target the agent or host.
- Ingestion points: The
validate_sim.shscript accepts a file path to an external Python script via positional arguments. - Boundary markers: The skill does not define specific delimiters or instructions to the LLM to ignore embedded content within the files it validates.
- Capability inventory: The skill has the capability to execute shell commands and run Python scripts via the
validate_sim.shscript. - Sanitization: While the script validates Python syntax and path resolution, it does not sanitize the internal logic or contents of the script before execution at Level 3.
Audit Metadata