ClawHub
Back to skill

Security audit

StickyHive

Security checks for vulnerabilities and agentic risk

Overview

StickyHive appears to be a legitimate community-management CLI, but it gives agents live authority to publish, delete, automate DMs, enroll members, and manage webhooks with limited safety guidance.

Install only if you intend to let an agent operate live StickyHive-connected communities. Prefer a test or least-privilege key, avoid exposing the key in prompts/logs/screenshots, and require explicit user approval before publishing, deleting, bulk scheduling, running or toggling workflows, changing sequence enrollments, or creating/deleting webhooks.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The README tells users to export a live production API key in a shell command example but provides no warning about credential sensitivity, least-privilege usage, or the risk of exposing environment variables in shell history, logs, screenshots, or shared terminals. In an AI-agent context this is more dangerous because users may install and run the tool in automated environments where secrets can be propagated broadly or mishandled by other tools.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger description is broad enough to match generic requests about community management, automation, engagement, or messaging, which can cause the agent to select this skill in situations where the user did not intend to invoke a high-impact external CLI. In this context, over-selection is risky because the skill can schedule posts, run workflows, send DMs, and manipulate live community state across multiple platforms.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The documentation exposes numerous destructive or externally impactful commands—such as delete, publish, bulk schedule, workflow run/toggle, sequence enrollment management, and webhook creation—without warning that they can modify live systems or contact real users. In a multi-platform community-management context, this increases the chance of accidental mass messaging, unwanted post publication, automation misuse, or data/configuration loss.

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
dist/index.js:32