team-coordinator

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to Indirect Prompt Injection (Category 8) due to its core delegation logic.
  • Ingestion points: Untrusted data enters via user requests starting with triggers like "帮我做..." (Help me do...), "分配任务" (Assign task), or direct mentions of sub-agents.
  • Boundary markers: The skill lacks explicit instructions to wrap user tasks in delimiters or provide "ignore embedded instructions" warnings when calling the message() or sessions_spawn() tools.
  • Capability inventory: The skill has the capability to execute message(action=send, accountId=...) and sessions_spawn(task=..., agentId=...), allowing it to pass potentially malicious payloads to specialized agents like xiaocode or xiaoops.
  • Sanitization: There is no evidence of escaping, validation, or filtering of user content before it is interpolated into delegation commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 07:56 AM