LLM Excessive Agency
Description
Detects LLM implementations with excessive autonomy allowing destructive operations without human approval.
What Shoulder detects
How to fix
Require human approval for sensitive operations and add iteration limits.
```go
if sensitiveOperations[toolName] {
queueForApproval(toolCall)
}
```
Learn more: https://shoulder.dev/learn/go/cwe-862/llm-excessive-agency
Applies to
Languages
References
Scan for this issue
Detect with Shoulder CLI
npx @shoulderdev/cli trust --rule=go-llm-excessive-agency .