ClawHub
Back to skill

Security audit

Pilot Service Agents Dev

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only helper for querying public developer-platform metadata through Pilot Protocol agents, with one documentation scope mismatch to review.

Before installing, confirm you are comfortable using Pilot Protocol service agents over network 9 and avoid sending private repository names, credentials, or sensitive queries. Treat the npm/package-registry overlap as a documentation/routing ambiguity rather than a security block.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest says "Do NOT use this skill" for Npm/PyPI/Maven registries, implying those ecosystems are out of scope for this skill. However, the documented agent list includes npm-search, jsdelivr-npm-stats, and several other language-package registries such as NuGet, Packagist, Pub.dev, and RubyGems, which materially broadens the stated scope beyond the manifest boundary.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.