Create Agent With Telegram Group
ReviewAudited by ClawScan on May 10, 2026.
Overview
The skill mostly matches its stated purpose, but it would use your logged-in Telegram browser session to create or manage groups, which is high-impact and not tightly scoped in the reviewed scripts.
Use this only if you are comfortable granting the agent write access to your OpenClaw config and carefully supervised access to a Telegram browser session. Prefer a dedicated Telegram profile/account, approve each Telegram action explicitly, confirm the exact model/group/chat_id before config changes, and review the generated workspace files.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
If approved, the agent may act in Telegram as the user and could affect groups or members beyond simple local configuration.
This directs the agent to operate through an existing logged-in Telegram account session, and the described scope includes deletion and member operations, not only creating one group.
Group creation/deletion and member operations should use browser automation (user-account flow). For browser flow, prefer Chrome relay profile for existing logged-in Telegram sessions.
Use a dedicated Telegram account or browser profile if possible, require step-by-step confirmation for each Telegram action, and limit automation to creating the named group and retrieving its chat_id unless the user explicitly requests more.
A wrong model, agent name, or chat_id could route Telegram messages to the wrong agent or make the agent respond without an @mention in the group.
The skill intentionally mutates OpenClaw routing and Telegram reply behavior. This is purpose-aligned and disclosed, but it is still a sensitive local configuration change.
scripts/provision_config.py reads and writes ~/.openclaw/openclaw.json ... updates only: agents.list ... bindings ... channels.telegram.groups.<chat_id>.requireMention=false
Before approving the config change, verify the agent name, model, chat_id, workspace path, and backup location; keep the generated openclaw.json backup.
Personal preferences or instructions placed in these files may persist and be reused by the new agent.
The skill creates persistent user, identity, and behavior files that can influence the new agent's future responses.
collect required values for USER.md / IDENTITY.md / SOUL.md ... then run: python3 scripts/init_workspace.py --workspace <workspace> --agent-name <agent_name>
Avoid placing secrets or highly sensitive personal data in USER.md, IDENTITY.md, or SOUL.md, and review those files after creation.