Security audit
Security checks for vulnerabilities and agentic risk
This is a broad agent-planning guidance skill, but its behavior is disclosed, non-executable, and includes verification and safety guardrails.
Install this only if you want a broad Indonesian-language agent-control and planning style to influence top-level tasks. Review its activation wording if you prefer narrower skill use, but no executable code, hidden persistence, credential handling, or destructive automation was found.
| Acting without a plan | Hierarchical planning first | | Losing state between steps | Track state explicitly | | Ignoring plugin orchestration | Coordinate multi-plugin flows | | No verification gate | Verify each milestone | ## Red Flags
NEVER FABRICATE NEVER CLAIM UNVERIFIED SUCCESS NEVER RETRY FOREVER NEVER IGNORE CURRENT STATE NEVER CONFUSE ASSUMPTION WITH FACT NEVER USE EXCESSIVE PRIVILEGE
No suspicious patterns detected.
