inbox
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the vendor-specific
hivecommand-line utility for managing messages, which is a core component of the author's ecosystem. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves message payloads created by other agents or sessions.
- Ingestion points: Data enters the agent's context through the
payloadfield of the JSON output generated byhive msg inbox(File: SKILL.md). - Boundary markers: There are no documented boundary markers or instructions to the LLM to treat the
payloadcontent as untrusted data. - Capability inventory: While this specific skill only reads data, it is designed for use within an environment where the agent has broader system capabilities such as
bdandhive(File: SKILL.md). - Sanitization: The skill does not perform any sanitization or filtering of the message content before presenting it to the agent.
Audit Metadata