ClawHub
Back to skill

Security audit

WebSim API

Security checks for vulnerabilities and agentic risk

Overview

This skill is a WebSim API helper with mostly read-only, purpose-aligned behavior, but users should be careful with the comment-posting token and avoid exposing internal project reasoning fields.

Install only if you want an agent to query WebSim data and, when explicitly asked, post comments using a user-supplied WebSim token. Do not ask it to retrieve or repeat internal reasoning fields such as site.yapping unless you are sure that content is appropriate to disclose.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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)

Ssd 3

Medium
Confidence
97% confidence
Finding
The skill explicitly documents `site.yapping` as "The AI's internal reasoning/thinking log" and presents it as a field to retrieve during project inspection. Exposing or encouraging access to internal reasoning can disclose sensitive implementation details, hidden prompts, secrets accidentally embedded in reasoning traces, or other non-user-facing data that should not be surfaced by default.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
This markdown file describes a state-changing POST action that sends user-provided content and a Bearer token to an external service. While it says authentication is required and not to post autonomously, it does not explicitly disclose the privacy/security impact of transmitting the comment and token to WebSim.

Static analysis

No suspicious patterns detected.