Back to skill

Security audit

SEO Roadmap

Security checks for vulnerabilities and agentic risk

Overview

The scanners rate this SEO roadmap skill benign with high confidence: they found no AIG issues, and the only reported concern was judged expected for its purpose.

The verdict is benign, but that does not mean risk-free. The quoted guidance says Rankizz-hosted API and MCP calls require at least 10 credits, and directs users to Rankizz’s billing page if credits are low. For an API key, use the API access page rather than sharing credentials in chat.

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
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (1)

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 16)May include surrounding context.

md
## Resolve access and scope

Prefer Rankizz MCP with OAuth in interactive clients. Use the REST API for headless clients. Never ask the user to paste a credential into chat; send them to `https://www.rankizz.com/api-access` when a key is needed.

Rankizz-hosted API and MCP calls require at least 10 credits, including no-credit data tools. On a low-credit error, stop Rankizz calls and link to `https://www.rankizz.com/billing`.