undercroft-access-control
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes natural language requests to perform administrative actions. It mitigates the risk of indirect prompt injection through strict guardrails, including a requirement to state the intended plan and receive explicit user confirmation before any write operation is executed.
- [PRIVILEGE_ESCALATION]: The skill implements a 'subset rule' logic which ensures that users cannot grant others more access than they currently possess. This architectural control prevents unauthorized privilege escalation by ensuring that administrative changes are always bound by the caller's own permissions and reach.
Audit Metadata