ClawHub
Back to skill

Security audit

Book Launch Coach

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only book publishing coach with broad but purpose-aligned advice and no executable or privileged behavior.

This skill appears safe to install as advisory publishing guidance. Users should treat its 2026 market claims, royalty figures, ad budgets, and platform details as planning suggestions that may need current verification before spending money or changing publishing strategy.

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 (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The manifest description includes many broad trigger phrases such as "writing a book," "book cover," and "author newsletter" that can match common user requests beyond a narrowly scoped launch-planning task. This can cause the skill to be selected in situations where it is not the best fit, increasing prompt-surface exposure and the chance that unrelated user content is routed into the skill unnecessarily.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The basic invocation examples use short, ambiguous requests like "Write a blurb for my book" and "My book stalled — diagnose," which do not clearly constrain when the skill should activate. Ambiguous examples can broaden routing behavior and cause overspecialized skill invocation for generic writing or advisory requests, though the downstream impact here is limited because the skill content itself is not performing privileged actions.

Static analysis

No suspicious patterns detected.