task-orchestrator
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill manages task lifecycles by ingesting user-provided data and executing CLI commands, creating a surface for potential injection.
- Ingestion points: User input for creating, assigning, and managing tasks, as well as the required
.agent-team/rules/index.mdconfiguration file. - Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the skill.
- Capability inventory: The skill executes shell-based CLI commands through the
agent-team tasksuite (create, list, show, assign, done, archive). - Sanitization: There is no evidence of validation or sanitization of user input before it is utilized by the CLI bindings.
Audit Metadata