ClawHub
Back to skill

Security audit

LinkSwarm

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed backlink-exchange API guide, but it should be reviewed because it can enroll domains and automate SEO-affecting link placements without meaningful authorization or risk guidance.

Install only if you control the domains involved and are comfortable using an automated backlink-exchange network. Confirm authorization before registering or verifying any site, review link partners and anchor text before publishing, and consider SEO, brand, and policy risks from automated outbound and inbound links.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (7)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill is explicitly designed to automate backlink exchanges, site registration, and link placement on user-controlled domains, but it does not warn that these actions modify a site's SEO posture and may create reputational, policy, or search-engine penalty risks. In an agent setting, presenting these operations as routine API steps without requiring explicit user consent increases the chance of unauthorized or poorly understood external actions affecting a user's web property.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
83% confidence
Finding

This endpoint transmits an email address to an external service to enroll in a waitlist and obtain API access. External transmission is expected for the feature, but it is still security-relevant because the skill encourages sending user/agent contact data to a third party without discussing trust boundaries, data handling, or consent.

Content

Scanner excerpt · SKILL.md (reported line 19)May include surrounding context.

1. Get API Key

bash
curl -X POST https://api.linkswarm.ai/waitlist \
  -H "Content-Type: application/json" \
  -d '{"email": "your-agent@example.com"}'

External Transmission

Medium
Category
Data Exfiltration
Confidence
83% confidence
Finding

This endpoint transmits an email address to an external service to enroll in a waitlist and obtain API access. External transmission is expected for the feature, but it is still security-relevant because the skill encourages sending user/agent contact data to a third party without discussing trust boundaries, data handling, or consent.

Content

Scanner excerpt · SKILL.md (reported line 19)May include surrounding context.

1. Get API Key

bash
curl -X POST https://api.linkswarm.ai/waitlist \
  -H "Content-Type: application/json" \
  -d '{"email": "your-agent@example.com"}'

External Transmission

Medium
Category
Data Exfiltration
Confidence
90% confidence
Finding

Registering a site with an external backlink-exchange network sends domain ownership and categorization data to a third party and enrolls the site into an automated SEO system. In context, this is more dangerous than a normal API call because it can operationally affect a user's site reputation, partner associations, and search-engine compliance without adequate warnings or authorization controls in the skill documentation.

Content

Scanner excerpt · SKILL.md (reported line 27)May include surrounding context.

2. Register Your Site

bash
curl -X POST https://api.linkswarm.ai/v1/sites \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"domain": "yoursite.com", "name": "Your Site", "categories": ["crypto", "fintech"]}'

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

The ownership verification step instructs users to place a DNS TXT record or meta tag, then notify the third-party service, which meaningfully changes a site's configuration and establishes trust with an external network. This is sensitive because an agent following these instructions could facilitate unauthorized enrollment of domains or alter site configuration without clearly surfacing the implications.

Content

Scanner excerpt · SKILL.md (reported line 36)May include surrounding context.

3. Verify Ownership

Add DNS TXT record or meta tag with verification token.

bash
curl -X POST https://api.linkswarm.ai/v1/sites/verify \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{"domain": "yoursite.com"}'

External Transmission

Medium
Category
Data Exfiltration
Confidence
92% confidence
Finding

Contributing link slots authorizes the external system to influence content placement on a user-controlled page, potentially creating outbound links that affect reputation, trust, and search-engine standing. In this skill's context, this is a substantive site-modification workflow disguised as a simple API call, making the omission of warnings and approval requirements security-relevant.

Content

Scanner excerpt · SKILL.md (reported line 43)May include surrounding context.

4. Contribute Link Slots

bash
curl -X POST https://api.linkswarm.ai/v1/contributions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{"page_url": "/resources", "max_links": 3, "categories": ["crypto"]}'

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

Requesting backlinks from the external network transmits target pages, desired anchor text, and categories to a third party for automated link-building. While expected for functionality, it creates risk because it can be used to manipulate search rankings, associate the site with questionable partners, or violate platform/search-engine policies, and the skill provides no cautionary framing.

Content

Scanner excerpt · SKILL.md (reported line 50)May include surrounding context.

5. Request Links

bash
curl -X POST https://api.linkswarm.ai/v1/requests \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{"target_page": "/", "preferred_anchor": "best crypto cards", "categories": ["crypto"]}'

Static analysis

No suspicious patterns detected.