zeno-claiming-tasks
Pass
Audited by Gen Agent Trust Hub on May 6, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes a local command-line interface called
probeto interact with a task management system. This tool is used for agent identification, capability management, task discovery, and claiming operations. These actions are consistent with the skill's stated purpose of task coordination. - [INDIRECT_PROMPT_INJECTION]: There is a potential attack surface for indirect prompt injection as the agent is instructed to read external content from task descriptions and project directives.
- Ingestion points: External data enters the context through
probe task get <task-id>andprobe message directives <project-id>commands inSKILL.md. - Boundary markers: The instructions do not specify any delimiters or warnings to ignore instructions found within the task data.
- Capability inventory: The skill allows the agent to execute further shell commands via the
probeCLI and send messages to other agents. - Sanitization: No validation or escaping of the task content is mentioned before it is processed by the agent. This represents a standard risk for agents processing external work items.
Audit Metadata