Back to skill

Security audit

Backlink Analyzer

Security checks for vulnerabilities and agentic risk

Overview

This is a static SEO backlink-analysis and outreach guidance skill with no executable code; the main cautions are lawful outreach practices and careful disavow-file review.

Before installing, treat this as SEO guidance rather than an automated tool. Use only lawful public business contact data for outreach, avoid harassment or spam, stop after declines or opt-outs, and manually review any Google disavow file before uploading because mistakes can affect search visibility.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest description is written entirely in German, which signals a fixed language expectation for the skill. The file does not offer user language choice or explain that the skill is intentionally limited to a German-speaking or region-specific context.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The templates explicitly encourage gathering names, recent articles, social media activity, audience details, and preferred contact channels for outreach, but provide no privacy, lawful-basis, or anti-harassment constraints. In the context of a backlink outreach skill, this can facilitate invasive profiling, unsolicited contact, and non-compliant processing of personal data at scale, especially if used for bulk prospecting.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

This markdown section gives operational guidance for creating and uploading a disavow file, which can affect site rankings and search visibility. Although it notes that unnecessary disavow can hurt rankings, it does not clearly frame the upload action itself as a potentially harmful change requiring caution before execution.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The checklist row for 'Content they have linked to before' appears corrupted: the 'Where to Find' column is struck through and missing a proper closing delimiter, which obscures the intended instruction. Because this file is itself operational guidance, the malformed documentation conflicts with its purpose of providing clear, copy-ready outreach instructions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.