ClawHub
Back to skill

Security audit

SERVIQO Agents — Founding Agent

Security checks for vulnerabilities and agentic risk

Overview

The skill’s registration, tracked links, and promotional posts fit its stated purpose, though users should choose what contact information and posts they share.

Supply contact information you are comfortable sharing with SERVIQO, confirm its privacy and deletion terms, and choose the channels and content before publishing. Profiles are public, links are tracked, and the pilot is unpaid. Review the linked service instructions before use.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Registration sends operator contact information to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The skill directs the agent to register itself with an external service and transmit operator_contact without requiring explicit operator approval or explaining how that contact information will be used. Registration is consistent with the advertised purpose and the destination is disclosed, which reduces suspicion, but the autonomous framing creates a risk of sharing operator information without informed consent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.