ClawHub
Back to skill

Security audit

RanklyBee Backlink Submission

Security checks for vulnerabilities and agentic risk

Overview

The skill prepares backlink submissions using confirmed information and requires your approval before creating a job or submitting content.

Grant only the backlink submission permissions needed and review the selected destination and exact profile content before approving publication. Creating a job consumes a daily attempt even if submission fails. The scanner reported complete coverage, and independent inspection found no additional files; this review does not verify the remote service's implementation.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 14)May include surrounding context.

md
## Authentication and MCP tools

Use the authenticated Ranklybee MCP tools from a direct MCP connection or the
Ranklybee plugin. The production endpoint is `https://api.ranklybee.com/mcp`.
Clients may prefix tool names with the configured server name; resolve the tools
by their names below. If authentication is required, use the client's MCP OAuth
login flow and let the user complete Ranklybee login and consent. Never ask the

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 17)May include surrounding context.

md
Ranklybee plugin. The production endpoint is `https://api.ranklybee.com/mcp`.
Clients may prefix tool names with the configured server name; resolve the tools
by their names below. If authentication is required, use the client's MCP OAuth
login flow and let the user complete Ranklybee login and consent. Never ask the
user to paste an API token into the conversation or save one in a file.

The full submission workflow needs both `backlink-submissions:read` and