ClawHub
Back to skill

Security audit

RanklyBee

Security checks for vulnerabilities and agentic risk

Overview

This skill provides scoped access to RanklyBee SEO data and requires approval before sending messages, publishing, or using write endpoints.

Grant only the projects and permissions you need, and keep tokens out of chat. Check every consent checkbox: the provider currently documents a preselected submission permission despite the skill's read-only-default claim. Keep approval prompts enabled for sending, posting, publishing, and other writes. This review covers the supplied instructions, not 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 (5)

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 25)May include surrounding context.

md
Webmaster Tools inside RanklyBee if you want search data.
3. Connect the agent in one of two ways:
   - **MCP (recommended):** add the remote server
     `https://api.ranklybee.com/mcp` (Streamable HTTP). The client opens a
     RanklyBee sign-in and consent page; choose the permissions to grant.
     Reading is on by default; anything that changes data, sends email or
     publishes stays off until the user turns it on.

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 32)May include surrounding context.

md
- **Public API:** create a token in RanklyBee under Settings > API access
     and send it as `Authorization: Bearer <token>`. Keep the token in the
     client's secret store or an environment variable such as
     `RANKLYBEE_API_TOKEN`; never ask the user to paste it into the chat.

Full setup guide for Cursor, Claude Code, Codex and other clients:
<https://ranklybee.com/docs/mcp>

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 59)May include surrounding context.

md
## Using the Public API

Base URL: `https://api.ranklybee.com/api/public/v1`
OpenAPI document: <https://api.ranklybee.com/api/public/openapi.json>

| Method | Path | Purpose |

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 77)May include surrounding context.

bash
curl -H "Authorization: Bearer $RANKLYBEE_API_TOKEN" \
  https://api.ranklybee.com/api/public/v1/projects

Write endpoints (queue outreach, reply to a thread, move a lead) act on the

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 60)May include surrounding context.

md
## Using the Public API

Base URL: `https://api.ranklybee.com/api/public/v1`
OpenAPI document: <https://api.ranklybee.com/api/public/openapi.json>

| Method | Path | Purpose |
| --- | --- | --- |