Use when an agent, harness, gateway, MCP workflow, or multi-step automation claims completion and the available traces, checkpoints, approvals, tool calls, or deployment records must be judged without trusting self-reported success.
no risky patterns detected
Type: Agent skill (SKILL.md) · Category: Security · Source: https://github.com/sickn33/agentic-awesome-skills/tree/HEAD/plugins/agentic-awes
| Capabilities (fewer powerful permissions = higher) | 50/50 |
| Maintenance | 35/35 |
| Documentation | 15/15 |
Always review files before installing. How scores work. Request a correction