afk-architect
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes a multi-agent orchestration framework, which creates an attack surface for indirect prompt injection when sub-agents (scouts, builders, pathfinders) process context or assignments.
- Ingestion points: Tasks and context are passed to sub-agents defined in
SKILL.mdandcrew.md. - Boundary markers: The skill explicitly instructs to "keep approvals with the user" and to provide "clear ownership" to agents, which acts as a procedural boundary.
- Capability inventory: The skill manages the spawning and configuration of sub-agents with varying model types and reasoning effort levels.
- Sanitization: There are no explicit instructions for sanitizing or escaping content before it is passed between the coordinator and sub-agents.
Audit Metadata