Seo Scout Pro

• Outcome: Review
• Latest audit: Sep 15, 2026 · 12:42 AM UTC
• Version: 1.0.0

Overview

This skill is mostly a backlink scouting guide, but it also teaches stealth browser automation and unsafe credential/session handling that users should review before installing.

Install only if you are comfortable with a skill that may guide agents toward automated backlink submissions and stealthy browser behavior. Use it only on sites where you have permission, avoid bypassing bot defenses, do not store passwords in project config files, and prefer manual submission or secure secret storage for authenticated workflows.

A.I.G

Vulnerability Patterns

• Insecure Skill Coding Practices: Finds exploitable flaws such as hardcoded secrets or command injection
• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally

Findings (1)

T09 · Insecure Skill Coding Practices

Warning

• Location: script.sh:228

Finding

Plaintext Credential Storage Guidance

Content

View full analysis

Remediation

View remediation

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection

Findings (12)

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence

Finding

The declared purpose is passive discovery and analysis, but the skill includes guidance for anti-detection and adapter generation for automated submission workflows, while not actually implementing the claimed analysis features. This mismatch can mislead users and reviewers about the real operational risk, masking functionality that could support evasive automation against third-party websites.

Content

No source excerpt is available for this finding.

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 · script.sh (reported line 148)May include surrounding context.

sh

```bash
URL="https://target-directory.com/submit"

curl -sL -A "Mozilla/5.0" "$URL" | python3 -c "
import sys, re

html = sys.stdin.read()

Description-Behavior Mismatch

High

• Category: Not specified by scanner
• Confidence: 97% confidence

Finding

The skill is described as a discovery and analysis tool, but this section provides concrete automation code to submit forms to third-party sites. That expands the capability from reconnaissance into active interaction, increasing abuse potential and creating a mismatch between declared purpose and actual functionality.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

High

• Category: Not specified by scanner
• Confidence: 99% confidence

Finding

Stealth and anti-detection capability is not justified by a scouting/form-analysis use case and directly supports concealment of automation from target sites. In this context, the guidance facilitates unauthorized automated access and weakens operators' visibility into bot activity.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

• Category: MCP Least Privilege
• Confidence: 85% confidence

Finding

The manifest advertises a marketing/form-analysis skill but does not declare any tool restrictions while static analysis detected shell-capable behavior. Undeclared execution capability increases the chance the skill can run commands outside user expectations, which is especially concerning in a skill adjacent to web automation and anti-detection workflows.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

• Category: Not specified by scanner
• Confidence: 96% confidence

Finding

An explicit 'anti-detect' command is a strong signal of intent to evade website defenses or scrutiny rather than merely analyze forms. In the context of backlink submission and automation, this capability can facilitate circumvention of access controls, bot detection, and site policies, making the skill materially more dangerous.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 90% confidence

Finding

Stealth or anti-detection behavior is presented without any warning about legal, policy, or system-integrity implications. That omission lowers user friction for misuse and normalizes evasion techniques in a context already aimed at automated submission workflows, increasing the likelihood of abusive deployment.

Content

No source excerpt is available for this finding.

Ssd 4

Medium

• Category: Not specified by scanner
• Confidence: 90% confidence

Finding

The authentication guidance normalizes storing credentials and reusing authenticated sessions for automated site access, including OAuth workflows. This can encourage unsafe account handling and automated use of third-party accounts in ways that may violate policy or expose sensitive sessions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 94% confidence

Finding

The skill advises storing credentials in a config file without any warning about secret handling, encryption, access controls, or accidental source control exposure. This can lead to credential leakage and unauthorized account use, especially in automation environments where config files are commonly shared or committed.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

• Category: Not specified by scanner
• Confidence: 98% confidence

Finding

The anti-detection section goes beyond form scouting by teaching stealth browser configuration and human-like evasion techniques. Even if framed as reliability guidance, it materially enables bypass of bot-detection systems unrelated to the advertised analysis purpose.

Content

No source excerpt is available for this finding.

Ssd 2

Medium

• Category: Not specified by scanner
• Confidence: 98% confidence

Finding

This section semantically promotes bypassing bot-detection by recommending patched browsers, webdriver masking, and human-like timing behavior. In a tool aimed at discovering and analyzing submission forms, that guidance meaningfully increases misuse risk beyond ordinary browsing automation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 98% confidence

Finding

Hard-coding locale and timezone without user opt-in can misrepresent client context and reduce transparency of automated access. While not severe on its own, in combination with stealth guidance it contributes to fingerprint spoofing and deception toward remote services.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.