Back to skill

Security audit

Parasite SEO Plan

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign with medium confidence: scanners found no AIG issues and one privacy-related concern about sending queries to third-party AI services, while Skillspector coverage was partial.

Consider whether queries you provide may contain confidential or personal information before installing or using the skill. The scanners report that such queries may be sent to third-party AI services without a privacy warning. The overall verdict is benign, but confidence is medium and Skillspector's analysis was partial because a local reference could not be resolved.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

The workflow sends user-supplied queries to third-party AI services without a privacy warning.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

Step 3 instructs the agent to submit representative user queries to external AI engines; line 50 gives similar instructions. Although these queries may come from user-provided research or Search Console data, the skill does not warn that they will be shared with third-party providers or require checking for confidential information before submission.

Content

No source excerpt is available for this finding.