local-pack-audit
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is to perform research on public local-pack and map results. It explicitly follows a 'read-only' policy, ensuring it does not attempt to modify business listings or perform unauthorized actions.
- [EXTERNAL_DOWNLOADS]: The skill references the UnifAPI MCP server and tools, which are hosted on the developer's infrastructure (unifapi.com). These references are necessary for the skill's intended functionality and do not involve untrusted third-party sources.
- [DATA_EXFILTRATION]: No sensitive data access or unauthorized network exfiltration patterns were detected. The skill uses OAuth for authentication to its data service, which is a standard and secure practice for managing API access.
- [PROMPT_INJECTION]: The instructions are clearly defined and do not contain patterns intended to bypass safety filters, extract system prompts, or override the agent's core behavioral constraints.
Audit Metadata