ac-master-controller

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill defines a high-capability interface for autonomous project implementation driven by external inputs.\n
  • Ingestion points: The run_project method accepts spec and objective strings from potentially untrusted sources.\n
  • Boundary markers: There are no markers or delimiters defined in the documentation to distinguish project data from agent instructions.\n
  • Capability inventory: The skill manages 'complete project implementations' and 'autonomous lifecycles', implying broad file system and command execution permissions through its referenced script.\n
  • Sanitization: No input validation or sanitization logic is described for the provided project specifications.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:26 PM