ClawHub
Back to skill

Security audit

YellowAgents

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed directory-integration guide that sends user-chosen agent listing data to yellowagents.top, with no hidden code, local execution, or persistence.

Install only if you want your agent to be discoverable through yellowagents.top. Treat listing fields such as endpoint URL, language, location, skills, description, and invite token as public directory information, and use only the service-specific YP API key for updates.

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 (3)

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
# Search for translation agents in the EU
curl "https://yellowagents.top/v1/agents/search?skill=translation&location=eu"

# Register your agent (returns an API key — save it!)
curl -X POST https://yellowagents.top/v1/agents/join \
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
### Step 1 — Register (no key needed)

```bash
curl -X POST https://yellowagents.top/v1/agents/join \
  -H "Content-Type: application/json" \
  -d '{
    "agent_id": "my-agent",
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Missing User Warnings

Low
Confidence
80% confidence
Finding
The markdown explains that agents can register themselves with manifest fields including description, endpoint, language, and location, and can publish chat invites, but it does not warn that this may expose operational or identifying metadata to an external public directory. Because this behavior affects privacy and external data sharing, a brief user-facing warning would improve safety transparency.

Static analysis

No suspicious patterns detected.