ClawHub
Back to skill

Security audit

agent-ready

Security checks for vulnerabilities and agentic risk

Overview

This skill is a site-audit and Ghost publishing workflow with sensitive but clearly disclosed CMS actions and built-in approval checks.

Before installing, make sure you are comfortable letting the agent use Ghost Admin credentials or a dedicated Ghost staff browser session to publish pages, append JSON-LD, and potentially configure redirects. Review the generated public copy before approval, use a dedicated staff account as the skill recommends, and confirm all changes are limited to the intended 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 181)May include surrounding context.

md
pointing `/llms.txt` at the raw URL. Use this only when the content needs to live in
  version control for other reasons (e.g., it's generated from repo content).
- Gate 2 applies: the owner approves the exact copy before publish.
- Verify with: `curl -s https://yourdomain.com/llms.txt/` and confirm real content
  comes back, not a 404 or a redirect loop.
- See `references/llms-txt-templates.md` for section-by-section templates by site type.

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · references/verification-commands.md (reported line 3)May include surrounding context.

md
# Verification Commands

All curl and shell commands used across the 9-item checklist, collected in one place
for quick reference. Run these as part of Gate 4 after each step — do not rely on API
success responses alone.

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · references/verification-commands.md (reported line 40)May include surrounding context.

Confirm the full block content:

text
curl -s -L https://yourdomain.com/ | python3 -c "
import sys, re
h = sys.stdin.read()
blocks = re.findall(r'<script type=\"application/ld\+json\">(.*?)</script>', h, re.DOTALL)

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · references/verification-commands.md (reported line 57)May include surrounding context.

Confirm the file is reachable and returns content:

text
curl -s -L https://yourdomain.com/llms.txt/

Validate at: https://llmstxt.cloud (paste live URL)

Static analysis

No suspicious patterns detected.