Zalo Agent CLI

Automate Zalo messaging, Official Account (OA), and MCP server integration via zalo-agent-cli. Triggers: 'zalo', 'send zalo', 'zalo OA', 'official account',...

This skill is an instruction-only wrapper for the external 'zalo-agent' CLI and appears coherent. Before using it: (1) obtain the zalo-agent binary from the official GitHub releases (verify checksums/signatures if available) — the skill does not provide or install the binary; (2) be careful when enabling listen --webhook: any configured webhook URL will receive message contents (PII), so only send events to endpoints you control and prefer HTTPS with authentication; (3) never publish or transmit exported credential files (creds.json, ~/.zalo-agent/*). The SKILL.md documents these risks and includes defensive guidance, but you should still avoid mass-forwarding contact lists or secrets without explicit user consent; (4) if you plan to run MCP or OA listeners on a VPS, protect endpoints with auth and firewall rules and confirm you understand proxy credentials handling. If you want higher assurance, review the zalo-agent project's source/release artifacts directly before installing the binary.

Type: OpenClaw Skill Name: zalo-agent Version: 1.3.0 The zalo-agent skill bundle is a comprehensive automation tool for Zalo, supporting personal accounts, Official Accounts (OA), and MCP integration. It provides a well-documented interface to the zalo-agent CLI with extensive command references and usage guides. Notably, the bundle includes a robust security model in SKILL.md and a detailed set of evaluation scenarios in evals/eval-scenarios.md specifically designed to instruct the AI agent to resist prompt injection, protect credentials (stored in ~/.zalo-agent-cli/ and ~/.zalo-agent/), and prevent data exfiltration. The capabilities, while powerful (including remote control via MCP and credential exporting), are strictly aligned with the stated purpose of Zalo automation and are accompanied by clear safety guardrails.