ClawHub
Back to skill

Security audit

README Auto Generator

Security checks for vulnerabilities and agentic risk

Overview

This README generator is a coherent documentation skill, but users should review generated configuration sections before publishing.

Install only for repositories you are comfortable having analyzed for documentation. Before publishing or committing the generated README, review configuration, environment-variable, endpoint, and internal-project sections to ensure no secrets or private details are disclosed.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (1)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly states it analyzes source code and detects environment variables, then generates README content from that analysis, but it provides no guardrails against surfacing secrets, internal endpoints, or sensitive configuration details in documentation. In a documentation-generation context, this is dangerous because generated README files are often committed to repositories or published publicly, turning accidental secret discovery into broad disclosure.

Static analysis

No suspicious patterns detected.