ClawHub
Back to skill

Security audit

Pilot Service Agents Language

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed language-service wrapper that sends user-directed queries to Pilot Protocol agents and external NLP providers, with no bundled code, persistence, or hidden behavior found.

Before installing, understand that queries may be sent over Pilot Protocol to remote agents and their upstream providers. Avoid sending secrets, credentials, confidential documents, or regulated personal data unless that sharing is acceptable for your use case.

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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs users to send arbitrary text to remote language and NLP agents and notes that some requests may reach premium or third-party upstream services, but it does not warn about privacy, confidentiality, or data-handling risks. In practice, users may submit sensitive prompts, names, documents, or regulated content to external services without informed consent, creating a real data exposure issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

The listed agent free-dictionary-en is explicitly English-only, but the skill text does not indicate that language constraints are optional, user-selected, or limited to specific use cases. This can conflict with locale/language policy expectations when a skill presents a constrained language path without offering or documenting user choice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.