ClawHub
Back to skill

Security audit

Skills

Security checks for vulnerabilities and agentic risk

Overview

This Markdown-only skill clearly discloses that it sends AetherLang flow code and user queries to an external API, with no local install, persistence, credentials, or hidden execution behavior found.

Install only if you are comfortable sending the AetherLang flow and your query text to api.neurodoc.app. Do not include secrets, credentials, personal account details, confidential business data, uploaded files, or hidden context in requests, and expect the agent to notify you before the first API call.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill description is extremely broad and does not define when the agent should or should not invoke the external service. Ambiguous scope increases the chance the agent will route unrelated or sensitive user requests to this API, causing unnecessary external data exposure and unexpected behavior.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
92% confidence
Finding

The skill is explicitly designed to transmit user-supplied flow code and query text to a third-party endpoint. Even though disclosure is present, this is still a real security/privacy boundary because broad skill scope and agent misuse could result in sensitive prompts or confidential business content being sent off-platform.

Content

Scanner excerpt · SKILL.md (reported line 13)May include surrounding context.

md
metadata:
  skill_type: api_connector
  external_endpoints:
    - https://api.neurodoc.app/aetherlang/execute
  operator_note: "api.neurodoc.app operated by NeuroDoc Pro (same as masterswarm.net), Hetzner DE"
  privacy_policy: https://masterswarm.net
license: MIT

External Transmission

Medium
Category
Data Exfiltration
Confidence
90% confidence
Finding

The documented API endpoint confirms that operation of the skill depends on external network transmission to a non-local service. This creates a data exfiltration surface if the agent includes more context than intended, and the surrounding marketing claims about safety do not eliminate the trust boundary.

Content

Scanner excerpt · SKILL.md (reported line 62)May include surrounding context.

API Endpoint

text
POST https://api.neurodoc.app/aetherlang/execute
Content-Type: application/json

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The Chef Omega example sets language="el", which forces Greek output for that workflow. Because the file does not frame this example as requiring explicit user preference at the point of use, it conflicts with the policy against imposing a language or locale without user opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.