ClawHub
Back to skill

Security audit

Smart README Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple README generator with no executable code, persistence, or hidden behavior, though users should avoid giving it sensitive private repository content unless they are comfortable sharing that context.

Before installing, treat any repository or source files you provide as potentially visible to the agent and its enabled network/model services. Do not provide private code, secrets, or proprietary project files unless that is acceptable in your environment.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly requires internet access and invites users to provide a repository or source files, but it does not warn that repository contents or code may be transmitted to external services during README generation. This creates a real data-handling and privacy risk, especially if users supply private repositories, proprietary source code, secrets accidentally committed to files, or other sensitive project content.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The skill provides only a generic example prompt, "Generate a README for my Express API project with Docker support," without defining explicit trigger phrases, scope constraints, or exclusion conditions. In a markdown skill description, this can make invocation conditions ambiguous because it is unclear what variations should or should not activate the skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.