team
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data via the
$ARGUMENTSparameter to coordinate sub-agents.\n - Ingestion points:
$ARGUMENTSinSKILL.md.\n - Boundary markers: Absent; user input directly drives sub-agent tasks.\n
- Capability inventory: Spawns sub-agents with code-implementation and testing roles via
TeamCreateandTaskCreate.\n - Sanitization: Absent.\n- [SAFE]: The skill uses legitimate orchestration tools and limits file access to project documentation context files like LORE.md.\n- [NO_CODE]: The skill consists entirely of markdown instructions for the agent and does not include any external code or scripts.
Audit Metadata