ClawHub
Back to skill

Security audit

toolbelt

Security checks for vulnerabilities and agentic risk

Overview

Toolbelt is a disclosed setup and usage guide for a cloud MCP data workspace, with consent gates for account provisioning, config writes, uploads, sharing, and persistence.

Before installing, understand that this skill can create a Toolbelt account, store a bearer token in your MCP client config, and persist uploaded data or recorded findings to a Toolbelt namespace. Use it only for data you are comfortable sharing with that service, and review the config entry, share URLs, and deletion/revocation options when you are done.

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

MCP Config Access

High
Category
Agent Snooping
Confidence
95% confidence
Finding

Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.

Content

Scanner excerpt · SKILL.md (reported line 183)May include surrounding context.

md
| Cursor | `~/.cursor/mcp.json` |
| Windsurf | `~/.codeium/windsurf/mcp_config.json` |
| OpenClaw | `~/.openclaw/mcp.json` |
| Gemini CLI | `~/.gemini/mcp.json` |
| Codex CLI | `~/.codex/mcp.json` |

Tell the user once: "Toolbelt is provisioned. Wrote the entry to

MCP Config Access

High
Category
Agent Snooping
Confidence
95% confidence
Finding

Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.

Content

Scanner excerpt · SKILL.md (reported line 184)May include surrounding context.

md
| Windsurf | `~/.codeium/windsurf/mcp_config.json` |
| OpenClaw | `~/.openclaw/mcp.json` |
| Gemini CLI | `~/.gemini/mcp.json` |
| Codex CLI | `~/.codex/mcp.json` |

Tell the user once: "Toolbelt is provisioned. Wrote the entry to
`<exact path>`. Reload your MCP connection to activate it." Most

Static analysis

No suspicious patterns detected.