Skills
skills/hkuds/openspace/code-exec-fallback/Gen Agent Trust Hub

code-exec-fallback

Fail

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: HIGHCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides explicit instructions to use the run_shell tool to execute Python scripts. This allows the execution of arbitrary commands in the host environment rather than a restricted sandbox.
  • [REMOTE_CODE_EXECUTION]: It details a multi-step process to 'write-then-execute' code (using write_file followed by run_shell). This pattern is a classic mechanism for achieving dynamic code execution outside of monitored boundaries.
  • [COMMAND_EXECUTION]: The instructions specifically target bypassing the restrictions of the execute_code_sandbox tool. This is a deliberate design to escape execution environments that may have security filters, dependency restrictions, or resource limits.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
May 15, 2026, 04:34 PM
Security Audit — agent-trust-hub — code-exec-fallback