ClawHub
Back to skill

Security audit

Configure File Write And Recovery

Security checks for vulnerabilities and agentic risk

Overview

This skill is meant for gateway configuration recovery, but it encourages persistent config overwrites without enough safeguards.

Review carefully before installing or using. Only run it in a controlled gateway environment after confirming the exact config path and desired model IDs, backing up the existing file, validating the resulting config, and requiring explicit approval for any write or restart action.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill demonstrates file-write and shell-capable behavior but declares no permissions, which hides its real execution capabilities from reviewers and policy controls. In practice this can enable unauthorized configuration changes and command execution in environments that rely on declared permissions for safety gating.

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding
The documented purpose is to help preserve configuration changes, but the included code instead overwrites a configuration file with hardcoded content and reads it back, which is materially different from implementing safe persistence or recovery logic. This mismatch can mislead operators into running destructive actions that replace existing configuration and introduce unintended models or settings.

Vague Triggers

Medium
Confidence
81% confidence
Finding
The trigger conditions are broad enough to activate on common configuration-related conversations, increasing the chance that risky file-overwrite and shell-based guidance is surfaced in contexts where it is not appropriate. Because the skill promotes direct config modification, overbroad triggering makes accidental misuse more likely.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill instructs users to overwrite configuration files and use exec-based commands without warning about backups, rollback, service disruption, or validation failure. In a gateway context, this can cause outages, loss of working configuration, or unintended persistent changes after reboot, making the operational risk significant.

Static analysis

No suspicious patterns detected.