ClawHub
Back to skill

Security audit

README Writer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward README-writing helper with no executable code, install steps, credential use, persistence, or hidden behavior.

This appears safe to install for README generation. Before using it on private repositories, consider whether you are comfortable sharing the relevant source files or project details with the agent so it can write accurate documentation.

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
  • 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
95% confidence
Finding
The skill advertises very broad trigger phrases such as "write a README for this" and "I need a README," which can match many ordinary user requests without strong scoping. In an agent environment, this increases the chance the skill is invoked in unintended contexts, causing overreach, incorrect task routing, or accidental processing of unrelated project content.

Static analysis

No suspicious patterns detected.