Back to skill

Security audit

Index Now

Security checks for vulnerabilities and agentic risk

Overview

This is a small documentation-only indexing skill whose network and credential needs are expected for its stated SEO purpose, with no hidden code or persistence.

Install only if you intend to submit URLs for sites you own or administer. Before using it, confirm the exact domain, URL list or sitemap, and target engines; keep Google service-account credentials and access tokens out of chat when possible and use secure secret handling.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

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 · SKILL.md (reported line 47)May include surrounding context.

md
1. Create a service account in Google Cloud Console
2. Enable the Indexing API
3. Add the service account email as an owner in Google Search Console
4. Generate an access token

## Supported Engines

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill describes submitting URLs and using Google service-account-based indexing, but it does not warn users that URLs, sitemap contents, API keys, service account identifiers, and related metadata may be transmitted to external services. This lack of disclosure can lead users to expose sensitive site structure or credential-related information without informed consent, especially in automated agent workflows.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill activates on a vague condition like 'when asked to submit URLs for indexing' without requiring explicit confirmation of target domains, ownership, scope, or user intent. That broad trigger can cause the agent to facilitate submission of arbitrary URLs to external indexing services, including third-party sites, making misuse easier and increasing the chance of unauthorized actions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.