ClawHub
Back to skill

Security audit

SEO & GEO Growth Agent

Security checks for vulnerabilities and agentic risk

Overview

This is a read-only SEO/GEO analysis skill that produces reviewable recommendations and explicitly avoids writes, secrets, code execution, and telemetry.

Install only if you want a read-only SEO/GEO assistant that prepares backlog-style recommendations. Keep it constrained to supplied or explicitly allowlisted sources, and use a separate authorized workflow for any publishing, CMS, analytics, or backlog changes.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 127)May include surrounding context.

md
This directory is portable: the loader should discover the root `SKILL.md` and

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 135)May include surrounding context.

md
This directory is portable: the loader should discover the root `SKILL.md` and

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/capability-detection.md (reported line 16)May include surrounding context.

md
For every capability used, record its name, availability, read-only status,
scope/limits, and an evidence reference. A tool is not approved merely because
it is present: reject capabilities that can publish, mutate, send, or access
secrets unless the current task is strictly read-only and the mutating mode is
not invoked.

Static analysis

No suspicious patterns detected.