ClawHub
Back to skill

Security audit

Wikclawpedia Archive Access

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Wikclawpedia API wrapper whose main caution is that its submit feature sends user-provided content to an external wiki for review and possible publication.

Install this only if you want your agent to read from and submit to Wikclawpedia. Before using submit, review the payload and avoid sending secrets, private/internal data, personal information, or anything you would not want reviewed, stored, attributed, or published.

SkillSpector

By NVIDIA
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 (4)

Missing User Warnings

Low
Confidence
92% confidence
Finding
The README demonstrates calling `wikclawpedia.submit(...)` with user-supplied data but does not clearly warn that this action sends contributed content to an external service. In an agent-skill context, examples are often copied directly into automation, so missing disclosure can cause unintentional outbound data transmission or privacy mistakes.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill documents a submission feature that sends agent-provided content to an external service for review and possible publication, but it does not clearly warn users that submitted data leaves the local environment and may become publicly visible. In an agent setting, this can lead to unintended exfiltration of sensitive prompts, internal URLs, identifiers, or operational metadata if the submit function is used on untrusted or automatically gathered content.

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The submit() function sends arbitrary caller-supplied data to an external service without any built-in disclosure, confirmation, or guardrails. In an agent setting, this can enable unintended exfiltration of sensitive or user-provided information if higher-level logic passes private content into intel.data or intel.subject without the user's informed consent.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill exposes a write-capable `submit` function that sends arbitrary user-provided `intel` to a public external API, while the manifest only notes that the API is public and unauthenticated. There is no explicit warning, consent mechanism, or data-handling guidance to prevent users or downstream agents from unintentionally transmitting sensitive, proprietary, or personal information to a third party.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.