ClawHub
Back to skill

Security audit

Pilot Service Agents

Security checks for vulnerabilities and agentic risk

Overview

This skill is a remote data-agent lookup helper, and its network behavior matches its stated purpose.

Install only if you are comfortable sending your queries and filters to Pilot Protocol service agents and, for some calls, Gemini-backed or upstream API services. Do not include secrets, credentials, regulated data, or confidential internal context in free-text prompts unless you have approved that data flow.

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
90% confidence
Finding

The skill explicitly instructs users to send queries to remote agents and retrieve responses from a network inbox, but it does not warn that prompts, filters, and returned data leave the local environment and may be visible to remote operators or upstream providers. In a skill designed to proxy many third-party data services, this omission can lead users to transmit sensitive queries or regulated data under a false assumption of local-only processing.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The free-text mode invites users to send arbitrary natural-language questions to remote agents, where the agent or its Gemini-backed processing may infer filters and then call upstream services. Without an explicit warning, users may include confidential context, credentials, internal identifiers, or personal data that are unnecessarily disclosed to external systems and potentially propagated beyond the Pilot overlay.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.