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 documentation is inconsistent and under-scopes sensitive data and token handling risks.

Review before installing. Only use this skill if you are comfortable exposing local inbox and browser-session status through a localhost web UI. Treat the dashboard URL token as sensitive, avoid sharing screenshots or logs containing it, and prefer explicit invocation only for this dashboard rather than broad security tasks.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The core description presents a local read-only dashboard that reads two local files and serves a local UI. Later sections discuss an 'LLM API', API-key leakage prevention, whitelist command execution, and HTTPS/network failure handling, which are not just incomplete details but actively conflict with the earlier minimal local-file-monitoring intent and imply substantially different capabilities.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The file repeatedly states the free version is limited to localhost on a fixed port and does not support LAN access or custom host/port settings. However, the documented capabilities list and troubleshooting sections also describe DASHBOARD_HOST=0.0.0.0, custom PORT, and multi-environment deployment, which contradict the stated free-version limitations and create ambiguity about actual behavior.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The documentation instructs users to access the dashboard via a URL containing the token and states that the page stores the token in localStorage, but it does not warn about the security implications. Tokens in query strings can leak via browser history, screenshots, logs, copy/paste, and referrer-like channels, while localStorage makes the token accessible to any script running in that origin, increasing the risk of unauthorized dashboard access.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger condition 'when the user needs to handle Security-related tasks, activate automatically' is overly broad and can cause the skill to run in contexts far beyond its stated purpose as a local monitoring dashboard. Unintended activation can expose inbox/session data to users or workflows that did not explicitly request this skill, increasing the chance of inappropriate data access or privacy leakage.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The description says '支持中文交互', and the document is written as if Chinese is the expected interaction language, without offering an opt-in choice or stating that the skill is intentionally region-specific. This may violate language/locale policy requiring user choice unless the restriction is clearly documented and justified.
Content: No source excerpt is available for this finding.