ClawHub
Back to skill

Security audit

clawvision

Security checks for vulnerabilities and agentic risk

Overview

ClawVision reads a user-selected OpenClaw session and creates local summary exports, with the sensitive behavior disclosed and gated by user confirmation.

Install only if you are comfortable letting the skill read the chosen chat session and write local HTML, PNG, Markdown, and PowerPoint files. Avoid using it on sessions containing secrets, credentials, personal data, or internal identifiers unless you have explicitly reviewed and approved exporting that content.

SkillSpector

Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Tp4

High
Category
MCP Tool Poisoning
Confidence
83% confidence
Finding
The top-level description is overly focused on 'explicit permission disclosure for security audit' and does not clearly summarize the skill's actual operational behavior, which includes reading session history, generating persistent artifacts, and invoking local execution/inference tooling. That mismatch can mislead users or reviewers about the real data-handling and execution scope, increasing the chance that sensitive session content is exported or processed without fully informed consent.

Static analysis

No suspicious patterns detected.