ClawHub
Back to skill

Security audit

page-metadata

Security checks for vulnerabilities and agentic risk

Overview

This is a plain SEO metadata guidance skill with no executable code, persistence, credential use, or hidden high-impact behavior.

This skill appears safe to install for SEO metadata assistance. Users should know it may read documented project-context files when present and should still review any generated meta robots or hreflang recommendations before applying them to a site.

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
81% confidence
Finding

The manifest says to use the skill whenever the user wants to optimize meta tags other than several excluded categories, and includes broad phrases like "other meta tags." That phrasing lacks clear negative examples or tighter constraints, so ordinary SEO discussions about metadata could trigger this skill unintentionally.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
78% confidence
Finding

The instructions direct the skill to read project context for language/locale and then identify multilingual setup using examples like zh, en, and x-default. This embeds locale expectations in the skill without stating that language selection should follow explicit user preference or that the scope is intentionally region-specific.

Content

No source excerpt is available for this finding.