skill-creator

Warn

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: MEDIUMPRIVILEGE_ESCALATIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [PRIVILEGE_ESCALATION]: The skill uses chmod to grant execution permissions to files generated at runtime. Evidence: scripts/init_skill.py calls example_script.chmod(0o755) for the newly created example.py file.
  • [DYNAMIC_EXECUTION]: The scripts/init_skill.py script programmatically assembles and writes new Python source files to the file system using internal string templates. Evidence: The create_resource_dirs function writes content to scripts/example.py.
  • [COMMAND_EXECUTION]: The skill instructions in SKILL.md provide specific shell command sequences for the agent to execute, which could be leveraged to perform unintended operations if the parameters were manipulated. Evidence: CLI usage examples for scripts/init_skill.py and scripts/quick_validate.py.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 3, 2026, 01:05 PM
Security Audit — agent-trust-hub — skill-creator