ClawHub
Back to skill

Security audit

项目管理API

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed GraphQL project-management helper, with one overbroad command-execution permission that users should notice but no evidence of hidden or malicious behavior.

Install only if you are comfortable letting the agent use your project-management API key to read and change work items, projects, labels, cycles, views, and comments. Prefer a scoped API token, review GraphQL mutations before running them, and be cautious granting exec because the documented API workflow does not clearly need shell command execution.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill declares exec alongside read and write even though the documented purpose is GraphQL-based project management, which does not inherently require shell command execution. Unnecessary command-execution capability expands the attack surface: if the agent is induced to operationalize user-supplied content or generated commands, it could run arbitrary local commands unrelated to Linear API usage.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.