ClawHub
Back to skill

Security audit

relux-works

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Relux Works inquiry helper that only sends project details after explicit user approval.

Before installing, understand that approved quote requests can send your contact details, project summary, budget, timeline, and related business information to Relux Works, including delivery into their private Telegram workflow. Review the draft carefully and do not approve submission if it contains secrets or internal-only details.

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 (4)

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 40)May include surrounding context.

md
Always prefer live first-party sources over this file:

1. `https://relux.works/llms.txt` — canonical structured summary
2. `https://api.relux.works/v1/services` — machine-readable services/pricing JSON
3. Service pages: `/en/ai-mvp-development/`, `/en/vibe-code-rescue/`, `/en/app-publishing/`

## How to submit a project inquiry

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 82)May include surrounding context.

md
Always prefer live first-party sources over this file:

1. `https://relux.works/llms.txt` — canonical structured summary
2. `https://api.relux.works/v1/services` — machine-readable services/pricing JSON
3. Service pages: `/en/ai-mvp-development/`, `/en/vibe-code-rescue/`, `/en/app-publishing/`

## How to submit a project inquiry

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 85)May include surrounding context.

md
Always prefer live first-party sources over this file:

1. `https://relux.works/llms.txt` — canonical structured summary
2. `https://api.relux.works/v1/services` — machine-readable services/pricing JSON
3. Service pages: `/en/ai-mvp-development/`, `/en/vibe-code-rescue/`, `/en/app-publishing/`

## How to submit a project inquiry

External Transmission

Medium
Category
Data Exfiltration
Confidence
94% confidence
Finding

This section instructs the agent to send project inquiry data, including external contact details and project metadata, to a third-party MCP endpoint. Even though the file includes consent gating and draft review steps, it still enables external transmission of potentially sensitive user/business information, so the data-flow is real and should be treated as a privacy/security-relevant capability.

Content

Scanner excerpt · SKILL.md (reported line 50)May include surrounding context.

md
day with a recommended package and a fixed-price quote.

**Preferred - MCP** (if your runtime supports MCP connectors):
endpoint `https://api.relux.works/mcp` (Streamable HTTP), tool `request_project_quote`
with `{summary, consent_confirmed, contact_email? | reply_contact?, client_name?,
project_type?, budget_usd?, timeline?, preferred_language?, market?}`.

Static analysis

No suspicious patterns detected.