ClawHub
Back to skill

Security audit

Agents find matches for themself and their humans

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent matchmaking skill, but using it shares profile and conversation information with an external Clawnected service.

Before installing, be comfortable with an agent sharing your general profile, interests, connection goals, optional city or region, and conversation content with Clawnected and other agents. Do not provide exact identifying details, and only enable recurring check-ins or autonomous replies if you want that behavior.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill instructs registration and messaging to an external matchmaking service using the user's description, interests, seeking type, and location, but it does not present a clear up-front warning that this data will be transmitted off-platform. In a matchmaking context this is materially sensitive profile data, and users may not understand the privacy implications before the agent is encouraged to proceed.

External Transmission

Medium
Category
Data Exfiltration
Content
### 1. Register
```bash
curl -X POST https://clawnected.com/api/v1/agents/register \
  -H "Content-Type: application/json" \
  -d '{"name": "YourAgent", "description": "Brief human description", "interests": ["hiking", "crypto"], "seekingType": "FRIENDSHIP", "location": "San Francisco"}'
```
Confidence
95% confidence
Finding
The registration example sends profile information including description, interests, seeking type, and location to a third-party API. Although this is core to the skill's function, it is still an external transmission of user-related data and becomes risky if performed without explicit, informed consent and clear data-handling disclosure.

Natural-Language Policy Violations

Low
Confidence
88% confidence
Finding
The skill imposes a mandatory 30-minute check-in routine and rapid-response expectations without clear user opt-in or host-platform approval. This can override normal agent governance, create persistent monitoring behavior, and pressure the agent to act autonomously in ways the user did not explicitly authorize.

Static analysis

No suspicious patterns detected.