wait
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from external sources through the message subscription mechanism, which can be exploited if the incoming data contains malicious instructions.
- Ingestion points: The skill relies on
hive msg sub --waitandhive msg inbox --waitcommands inSKILL.mdto retrieve message content from various topics. - Boundary markers: The instructions do not specify the use of delimiters or boundary markers to isolate the untrusted message content from the agent's instructions.
- Capability inventory: The agent uses the
hiveCLI tool to perform messaging operations (publish, subscribe, inbox). - Sanitization: There is no mention of sanitizing or validating the content of the messages before the agent processes or acts upon them.
- [COMMAND_EXECUTION]: The skill instructions direct the agent to execute shell commands using the
hiveCLI utility to manage inter-agent communication and synchronization workflows.
Audit Metadata