ClawHub
Back to skill

Security audit

StockScanner Pro

Security checks for vulnerabilities and agentic risk

Overview

This skill is openly for social-media automation, but it needs review because it can publish or reply from public accounts and relies on sensitive account credentials with limited guardrails.

Before installing, treat this as granting an agent the ability to act from your social accounts. Use the least-privileged platform tokens available, avoid browser cookies where possible, keep dry-run and manual review enabled, and do not enable scheduled or auto-reply workflows until you have clear approval, rate limits, and a way to disable them quickly.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill automates posting and comment replies on third-party social accounts, but the description lacks warnings that it can take actions affecting public-facing external accounts. Without clear disclosure and confirmation requirements, users may unintentionally authorize mass posting, unwanted replies, reputational damage, or policy-violating automation.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The configuration instructs users to place sensitive credentials such as API keys, secrets, cookies, and access tokens in a local config file without any security guidance. This increases the chance of credential leakage through weak file permissions, backups, logs, accidental sharing, or compromise of the local environment, potentially leading to full takeover of connected social accounts.

Static analysis

No suspicious patterns detected.