inbox
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
hivecommand-line utility to interact with the messaging infrastructure. The--sessionflag allows user-provided input to be passed as an argument, which is the standard method for specifying session targets in this environment. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests untrusted data from other agent sessions through message payloads.
- Ingestion points: Data is retrieved from the
agent.<id>.inboxtopic via thehive msg inboxcommand inSKILL.md. - Boundary markers: No specific delimiters or safety instructions are provided to the agent to distinguish between the untrusted message content and its primary instructions.
- Capability inventory: The skill environment allows for reading messages (
hive msg inbox), viewing task details (hive hc show), and sending messages to other agents (/hive:publish). - Sanitization: The documentation does not specify any content filtering or sanitization for incoming message payloads before they are processed by the agent.
Audit Metadata