simulation-platform-engineer

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it is designed to ingest and parse external data sources like Waymo logs and OpenSCENARIO XML files. Evidence: (1) Ingestion points: Data entering via log loading in 'references/pitfalls.md'. (2) Boundary markers: No explicit instructions to ignore instructions in external data. (3) Capability inventory: Subprocess and Kubernetes command usage. (4) Sanitization: No input validation for external content.
  • [COMMAND_EXECUTION]: The skill provides numerous examples of shell commands for simulation management and uses Python's subprocess module to manage local simulation processes.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 01:57 AM