ClawHub
Back to skill

Security audit

ZARZOOM

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed ZARZOOM social-posting integration that uses a customer API key for posting, status, calendar, and analytics actions; I found no hidden or unrelated behavior.

Install only if you are comfortable letting OpenClaw submit content and media to ZARZOOM and eventually to connected social accounts after ZARZOOM compliance review. Use the least-privileged ZARZOOM key scopes you need, keep the local config private, rotate the key if exposed, and confirm platform targets before any posting or calendar-edit action.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The README states the skill will activate automatically when the assistant detects 'ZARZOOM-relevant intent,' but does not define a narrow invocation boundary. For a skill that can submit external content and use customer API keys, ambiguous auto-activation increases the chance of unintended tool execution, accidental posting actions, or invocation from loosely related prompts.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill clearly sends user-supplied articles, images, videos, submission metadata, and analytics queries to an external service, but the user-facing description does not prominently warn about that third-party data transfer. This can mislead users into sharing sensitive business content or analytics without informed consent, especially because the skill also involves admin compliance review by ZARZOOM.

Session Persistence

Medium
Category
Rogue Agent
Content
primaryEnv: ZARZOOM_API_KEY
envVars:
  - name: ZARZOOM_API_KEY
    description: Your ZARZOOM developer API key. Create one at https://zarzoom.com/dashboard/api-keys.
    required: true
requires:
  env: ["ZARZOOM_API_KEY"]
Confidence
84% confidence
Finding
The skill instructs users to place a long-lived API key directly into a local persistent configuration file, which increases the chance of credential exposure through filesystem compromise, backups, screenshots, or accidental sharing of config files. Because the key authorizes content publication and access to workspace analytics/status data, theft could let an attacker post content or inspect account activity.

Session Persistence

Medium
Category
Rogue Agent
Content
- **`401 unauthorized`** — the `ZARZOOM_API_KEY` is missing, malformed,
  or revoked. Tell the user:
  > "Your ZARZOOM API key isn't working. Create a new one at
  > https://zarzoom.com/dashboard/api-keys and paste it into
  > `~/.openclaw/openclaw.json` under `skills.entries.zarzoom.env.ZARZOOM_API_KEY`."
Confidence
88% confidence
Finding
The 401 recovery guidance tells users to paste a replacement API key into a persistent config path, reinforcing insecure secret handling and normalizing storage of live credentials in plaintext-like local configuration. Repeatedly steering users toward persistent storage increases exposure risk for powerful `zarz_live_*` keys that can read usage/status data and submit or manage posts.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.