isaac-sim-migration
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of local scripts and Isaac Sim runtime environments, specifically
audit_isaac_sim_6_0.pyandpython.sh, to perform migration audits and runtime validation. These are standard operations for development and migration tasks. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it ingests and processes untrusted data from a user-provided project directory to generate inventory reports. This risk is inherent to the skill's primary purpose of auditing external projects.
- Ingestion points: Files within the directory specified by the
$WORKSPACE_DIRenvironment variable. - Boundary markers: The instructions do not define specific markers or delimiters to isolate untrusted project data from the agent's reasoning processes.
- Capability inventory: The skill utilizes shell execution for auditing and running simulation validation tasks.
- Sanitization: No input validation or output sanitization for the project files being audited is specified.
Audit Metadata