ClawHub
Back to skill

Security audit

Entity Registry

Security checks for vulnerabilities and agentic risk

Overview

This is a scoped entity and knowledge-graph audit skill with gated registry writes; some checklist items drift into marketing recommendations, but they are disclosed and not hidden or automatic.

Install this only if you want the agent to audit or maintain canonical entity records. Review any proposed persistent registry write before approving it, and treat PR, topical content, robots/crawlability, or page-level GEO recommendations as handoffs rather than automatic actions by this skill.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The document introduces broader content authority and SEO-style work such as topical content depth, author credential pages, original research, and natural entity mentions, which exceed machine-facing entity registry maintenance. In an agentic setting, these instructions can steer execution toward editorial, content, and marketing operations that the declared skill is not supposed to control.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The checklist explicitly extends the skill into AI recognition, AI overview presence, crawlability for AI bots, and GEO/page-level optimization, which the manifest says should be handled by a different skill. This scope drift can cause an agent to perform actions outside its authorized domain, increasing the chance of misrouting user requests, applying the wrong playbook, or making unintended changes to content strategy and indexing controls.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The action plan template directs PR, topical cluster development, and recurring AI testing, which are operational marketing activities beyond entity registry maintenance. Because templates are high-leverage guidance for agents, this can systematically induce out-of-scope actions and blur separation between identity governance and broader growth/visibility work.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

This manifest enumerates package metadata and files but provides no trigger phrases, activation conditions, or exclusion criteria. For manifest files, missing specificity on trigger scope can make it unclear when the skill should activate versus not activate.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.