ClawHub
Back to skill

Security audit

Skills

Security checks for vulnerabilities and agentic risk

Overview

This skill only guides style analysis and style-based drafting from user-provided text or images, with no code execution, persistence, or hidden data access.

Install only if you want style-analysis and style-imitation help to trigger on broad tone, style, and reference-text requests. Review generated outputs for copyright-sensitive similarity to the source, especially when using long or recognizable reference works.

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
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill defines very broad activation criteria, including generic requests to analyze writing style or imitate a reference text, which can cause the agent to invoke this skill on ordinary writing-help prompts without clear user intent. Overbroad routing increases the chance of unintended behavior, policy bypass through misclassification, and application of style-copying behavior in contexts where a narrower or safer skill should have handled the request.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The natural-language trigger examples are ambiguous and lack exclusion rules, so common requests like analyzing tone or writing in a similar style may activate the skill even when the user did not intend to invoke specialized style-extraction behavior. In this context, that is more dangerous because the skill is specifically designed to extract and reproduce stylistic features from supplied material, increasing the risk of inappropriate routing and downstream misuse.

Content

No source excerpt is available for this finding.