ClawHub
Back to skill

Security audit

Phy Devto Post

Security checks across malware telemetry and agentic risk

Overview

This skill is transparent about publishing to DEV.to through Chrome, but it gives an agent high-impact posting authority without a clear final confirmation step.

Install only if you are comfortable letting an agent control your real Chrome session and publish through the DEV.to account currently logged in. Use a separate Chrome profile or test account when possible, review the exact title, tags, body, and published state, and require a manual final confirmation before any command that posts with published:true or clicks Publish.

SkillSpector

By NVIDIA
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 (2)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The manifest description includes broad activation language such as "write dev.to post" and "any DEV.to publishing request," which can cause the skill to trigger in situations where the user did not explicitly consent to browser automation and live publishing. In this skill, that risk is amplified because activation leads to controlling the user's real Chrome session and posting through an authenticated account.

Missing User Warnings

High
Confidence
98% confidence
Finding
The skill description does not clearly warn that it will drive the user's real Chrome browser, rely on an existing logged-in DEV.to session, and publish content to a live account. Because the skill uses AppleScript and authenticated browser state to perform irreversible external actions, the absence of a prominent warning increases the chance of accidental publication or misuse under mistaken user expectations.

VirusTotal

No VirusTotal findings

View on VirusTotal

Static analysis

No suspicious patterns detected.