ClawHub
Back to skill

Security audit

Front

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Front integration that can read and modify Front data and optionally set up Maton automations, with explicit approval and credential-handling safeguards.

Install only if you are comfortable granting Maton/Front access to the connected workspace. Review any write operation, hosted function, trigger, destination, or --exec watcher before approving it, because those can modify shared Front data or run ongoing automation. Prefer the CLI OAuth flow over raw API keys and do not allow credentials or broad event payloads to be forwarded to third-party hosts unless that is the explicit task.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest description narrows the skill to Front communication/team resources and says the documented endpoints are the ones this skill uses. However, the file later exposes additional operational areas: Front accounts, channels, and comments, plus extensive Maton-hosted automation primitives such as functions, triggers, and destinations. Those are materially broader than the concise capability statement at the top.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest frames this as a Front API integration for managing Front resources. Even though the document warns that --exec is out of scope unless explicitly requested, it still documents a capability to run arbitrary local scripts on event data, which is a qualitatively different capability from API interaction with Front. That execution capability is not necessary for the skill's stated default purpose.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.