ClawHub
Back to skill

Security audit

market-recon

Security checks for vulnerabilities and agentic risk

Overview

This skill is a scoped GitHub-only research workflow that produces a chat report without writing files or requesting privileged access.

Install only if you want an agent workflow that can fetch GitHub pages and APIs for market research. Expect it to use limited subagents on larger runs, but it should not write files or access non-GitHub sources unless you explicitly change its constraints.

SkillSpector

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

Static analysis

No suspicious patterns detected.