ClawHub
Back to skill

Security audit

Package SEO

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only SEO guidance skill with no code execution, persistence, credential access, or hidden data handling, though users should check that suggested keywords and compatibility claims are accurate.

Before installing, understand that this skill is marketing-oriented: review any generated package descriptions, tags, README sections, and 'Works With' claims for factual accuracy and relevance before publishing them publicly.

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
88% confidence
Finding

The skill's activation guidance is very broad: it applies to publishing, updating, and auditing across npm, GitHub, and skill platforms without clear exclusions or user-intent checks. In an agent setting, this can cause the skill to trigger in situations where SEO optimization is not the user's goal, leading to unsolicited marketing-oriented modifications and increased risk of policy drift or inappropriate recommendations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

The skill instructs users to 'always include' a fixed set of English-language branding and trend keywords, with no opt-in for locale, audience, or accuracy constraints. In practice this can push an agent to insert irrelevant or misleading terms into package metadata, producing spammy outputs, degrading trust, and creating discoverability manipulation or misrepresentation risk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.