ClawHub
Back to skill

Security audit

tock-mcp

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed, read-only Tock MCP integration that uses a signed-in browser session for restaurant discovery and reservation lookup.

Before installing, make sure you trust the tock-mcp npm package and the ContextMint Bridge extension, because account tools use your signed-in Tock browser session and can return profile and reservation information. The artifact describes the integration as read-only and does not provide booking, cancellation, or payment actions.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (3)

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 21)May include surrounding context.

1. Install the MCP server

Add to .mcp.json in your project or ~/.claude/mcp.json:

json
{

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 122)May include surrounding context.

md
Passing `view` to one of those is not an error and will not fail: the tool
does not declare it, so zod drops the unknown key and the call runs exactly as
it would have. You get no warning, so a successful call is not evidence the
rung was honoured.

## Typical flow

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 68)May include surrounding context.

md
Two tools take `view: "compact" | "full"` — `tock_get_restaurant` and
`tock_get_profile` — and **`compact` is the default**, so you get the slim
rung without asking for it. The other six of this server's eight tools have no
`view`; each for its own reason, below.

**Compact here is media stripping, not a field projection.** `src/view.ts`

Static analysis

No suspicious patterns detected.