Kim Msg Skill

PassAudited by ClawScan on May 1, 2026.

Overview

This skill is a coherent Kim messaging integration, but users should notice that it reads local Kim credentials and can send messages to users or group chats when invoked.

This appears safe for its stated purpose if you intend to let an agent send Kim notifications. Before installing, make sure the Kim app or webhook is least-privileged, protect the credential files, and require confirmation for important or sensitive messages.

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.

What this means

If invoked, the skill can use configured Kim credentials to send messages as the associated app or bot.

Why it was flagged

The script can load Kim credentials from environment variables or local secret files. This is disclosed and purpose-aligned, but those credentials authorize message sending.

Skill content
const CREDENTIAL_FILES = [ path.join(os.homedir(), '.openclaw', '.secrets'), path.join(os.homedir(), '.kim_credentials'), path.join(process.cwd(), 'kim_credentials') ];
Recommendation

Use least-privileged Kim credentials, keep secret files permission-restricted, and verify the target user or group before sending.

What this means

An accidental or poorly reviewed invocation could send the wrong content to the wrong Kim user or group.

Why it was flagged

The script posts user-provided message content to Kim users via API endpoints. This matches the skill purpose, but it is an external account action.

Skill content
const url = `${BASE_URL}/openapi/v2/message/send`; ... username: targetUser, ... const url = `${BASE_URL}/openapi/v2/message/batch/send`; ... usernames: [targetUser]
Recommendation

Ask the agent to confirm message text and recipient before invoking the skill, especially for group chats or business-sensitive content.

What this means

The skill may fail until required local tools are available, and users may need to install them manually.

Why it was flagged

The metadata under-declares runtime requirements even though the included scripts use Node.js, bash, curl, and jq. This affects install clarity rather than showing hidden behavior.

Skill content
Required binaries (all must exist): none ... Install specifications: No install spec — this is an instruction-only skill.
Recommendation

Install dependencies only from trusted sources and prefer updated metadata that declares required binaries and credentials.