worker-inspector
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is strictly limited to read-only operations and includes explicit routing logic to prevent unauthorized actions like dispatching or replying.
- [COMMAND_EXECUTION]: The skill utilizes a local command-line interface,
agent-team worker status, to perform its primary function of inspecting worker states. - [PROMPT_INJECTION]: Although the skill reads a local rule file (
.agent-team/rules/index.md) which could theoretically contain instructions, the risk is mitigated by the skill's restricted read-only scope and absence of high-privilege capabilities.
Audit Metadata