ClawHub
Back to skill

Security audit

README Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill reads normal project files to draft a README and asks before overwriting an existing README.

This skill is reasonable to install if you want an agent to inspect a repository and generate README content. Be aware that its trigger phrases are broad, so confirm the agent is acting on the intended project, and review generated README changes before accepting them, especially when a README.md already exists.

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 (3)

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
95% confidence
Finding
The trigger phrase 'create readme' overlaps with the generic built-in command namespace 'create', making it susceptible to shadowing or accidental interception of requests intended for core tooling. In practice, this can reroute normal create operations into this skill, causing unintended repository scanning and documentation generation behavior.

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
95% confidence
Finding
The trigger phrase 'write readme' conflicts with the generic built-in command namespace 'write', creating ambiguity over whether the user intended a core write action or this custom skill. This ambiguity can lead to accidental activation and unintended file generation or overwrite flows in the project root.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger phrases are generic documentation-related commands that could match ordinary user intent without sufficient scoping to this specific skill. That increases the chance of unintended invocation, especially in environments with multiple skills or built-in commands, which can cause the agent to perform file analysis and potentially overwrite or propose overwriting README files unexpectedly.

Static analysis

No suspicious patterns detected.