aiox-squad-creator
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions require the agent to execute a local script using the command
node .aiox-core/development/scripts/generate-greeting.js squad-creatorduring the activation protocol. - [DYNAMIC_EXECUTION]: The skill relies on external logic by loading agent personas and command systems from local files (
.aiox-core/development/agents/squad-creator.md) and executing scripts at runtime to determine its behavior. - [INDIRECT_PROMPT_INJECTION]: The skill adopts instructions and personas from external project files, which represents a surface for instructions embedded in data.
- Ingestion points:
.aiox-core/development/agents/squad-creator.mdand.codex/agents/squad-creator.md(SKILL.md). - Boundary markers: None specified; the agent is instructed to "Adopt this agent persona and command system" directly from the source.
- Capability inventory: The skill possesses command execution capabilities via
nodeand file system read access for the source of truth files. - Sanitization: No explicit sanitization or validation of the loaded markdown content is described.
Audit Metadata