ClawHub
Back to skill

Security audit

Aic Dashboard Free

Security checks for vulnerabilities and agentic risk

Overview

The skill is a local dashboard for inbox and browser-session monitoring, but its sensitive-data access is paired with overly broad activation guidance and weakly scoped authority.

Install only if you specifically want a local dashboard that reads ./data/inbox.jsonl and ./data/session.json. Treat the dashboard URL token as sensitive, avoid exposing the service beyond localhost, and review any actual Node script before running it because this package describes execution but does not include the referenced implementation file in the inspected artifact.

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 (2)

Vague Triggers

Medium
Confidence
78% confidence
Finding
The trigger condition 'when the user needs to handle Security-related tasks, auto-activate' is overly broad and can cause the skill to run in contexts far beyond its intended purpose. Because this skill exposes inbox and session-monitoring functionality, ambiguous auto-activation increases the chance of unnecessary access to sensitive local data and accidental disclosure in unrelated workflows.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill handles sensitive mail and browser session data in a web UI and later states that the access token is stored in browser localStorage, but the description does not clearly warn about those risks. localStorage is readable by any script running in the same origin, so if the dashboard ever suffers XSS or unsafe content rendering, the token and access to sensitive monitoring data could be exposed.

Static analysis

No suspicious patterns detected.