ClawHub
Back to skill

Security audit

ENT Meta Connect

Security checks for vulnerabilities and agentic risk

Overview

This skill stores a user-provided Meta Ads token and restarts the gateway, but those actions are clearly disclosed and aligned with connecting Meta Ads.

Install this only if you want the agent to store a Meta Ads access token in the gateway environment and restart the gateway. Treat the token as sensitive, confirm the agent is acting for the machine/account owner, and rotate the token if it was pasted into chat or later no longer needed.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger phrases are very broad and cover ordinary configuration/help requests, which increases the chance this skill activates in situations where a user did not explicitly intend credential storage and gateway reconfiguration. In this skill’s context, accidental activation is more dangerous than usual because the workflow handles sensitive Meta access tokens, modifies persistent environment configuration, and restarts infrastructure.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The description and operational text are written as if the skill is intended to run in Vietnamese, including prescribed user-facing phrasing in Step 6, but there is no opt-in or note that the skill is region- or language-specific. Under the policy, forcing a specific language without user choice is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.