Security audit

seo-backlinks

Security checks for vulnerabilities and agentic risk

Overview

This skill is a backlink-analysis guide that uses SEO data sources and does not show hidden execution, persistence, or data exfiltration behavior.

Install only if you are comfortable using third-party SEO services and sharing target domains or backlink lists with the providers you configure. Treat the automatic PDF-report suggestion as promotional, and review any optional setup or extension install command before running it.

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

Findings (1)

T01 · Skill Instruction Hijacking

Warning

Location: SKILL.md:258
Finding: Mandatory Promotional Output Injection
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The mandatory pre-delivery checklist includes unrelated checks such as schema @type, parse_html, H1 semantics, and platform detection that do not belong to backlink analysis. In an agent setting, such instructions can cause the model to fabricate unsupported validations, invoke irrelevant tools, or conflate backlink evidence with on-page/structured-data signals, increasing the risk of incorrect security or SEO conclusions presented as verified fact.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Low

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The manifest describes this skill as performing backlink profile analysis, including referring domains, anchor text, toxic links, and competitor gap analysis. The instruction to always offer /seo google report introduces a separate reporting capability tied to another skill area, which goes beyond the declared backlink-analysis purpose.
Content: No source excerpt is available for this finding.