ClawHub
Back to skill

Security audit

Docs Refresh

Security checks for vulnerabilities and agentic risk

Overview

This documentation-refresh skill is coherent with its stated purpose and does not show hidden networking, credential access, persistence, or destructive behavior.

Install this only if you are comfortable with an agent reading your repository state and diffs and editing documentation files. The bundled shell collector is local and git-focused, but review it if your repository contains sensitive unreleased changes.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The default prompt grants a broad, loosely constrained workflow: it instructs the agent to traverse the repository, resolve the skill directory, execute a bundled collector when possible, route based on discovered configuration, and modify authoritative documents. Because trigger conditions and trust boundaries are not narrowly defined, an attacker who can influence repository contents, AGENTS.md, routing config, or the bundled collector may steer the agent into unsafe actions, excessive file access, or unintended documentation changes.

Static analysis

No suspicious patterns detected.