ClawHub
Back to skill

Security audit

onthecheap-mcp

Security checks for vulnerabilities and agentic risk

Overview

This is a read-only local events and deals guide with no credential use, persistence, or system-changing behavior in the artifact.

This skill appears safe to install for browsing public On the Cheap listings. Users should still remember that event and deal availability can change and should verify details with the source before making plans.

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
  • 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 (1)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
## Response shape (`view`)

`otc_search_posts` takes `view: "compact" | "full"`, and **`compact` is the
default** — you get the slim shape without asking. It is the only tool here
that takes one; the other seven are covered at the end of this section.

Compact projects each result down to the fields a caller ranks or browses on:
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.

Static analysis

No suspicious patterns detected.