ClawHub
Back to skill

Security audit

clawbox-link-to-docs

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says: it turns a user-provided link into Feishu source and analysis documents, with normal privacy considerations for uploading content to Feishu.

Install this only if you are comfortable with the agent fetching the link you provide and writing the full captured text plus source metadata into Feishu. Avoid using it on confidential, internal, paywalled, personal, or regulated content unless your Feishu workspace is approved for storing that material.

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 (3)

Hidden Instructions

High
Category
Prompt Injection
Content
# clawbox

OpenClaw skill: turn a shared web link into two Feishu docs (source archive + analysis summary).
Confidence
60% confidence
Finding
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill directs the agent to fetch arbitrary external URLs and then create or update Feishu documents containing the captured content and source metadata, but it does not require notifying the user that article contents, URLs, titles, and capture timestamps will be transmitted to a third-party platform. This creates a privacy and data-handling risk, especially if users provide internal, paywalled, sensitive, or personal links under the assumption the task is only local or ephemeral.

Natural-Language Policy Violations

Low
Confidence
95% confidence
Finding
The template headings and instructions are entirely in Chinese, which implicitly requires responses in a specific language. The policy forbids forcing a language or locale unless the user is given a choice or the constraint is clearly justified.