omh-live-info
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a shell command
omh runtime record --skill live-info-operator --harness live-info-operator --status startedto track the state of the workflow. This command utilizes theomhCLI tool. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection by processing untrusted data.
- Ingestion points: User-provided queries for weather, stock prices, sports scores, and map directions (SKILL.md).
- Boundary markers: The skill mentions 'freshness boundaries' for data staleness but lacks explicit delimiter or boundary markers to separate untrusted user input or external tool outputs from the agent's instructions.
- Capability inventory: The agent is authorized to execute shell commands (
omhCLI) and use external tools such as web search, maps, and financial quote tools (SKILL.md). - Sanitization: No evidence of input sanitization or escaping of external content before it is interpolated into the workflow or tool calls.
Audit Metadata