Back to skill

Security audit

AI Brand Facts

Security checks for vulnerabilities and agentic risk

Overview

The skill is rated benign because the scanners found no reported code or instruction hijacking, while flagging a privacy disclosure gap in an optional workflow; confidence is medium and coverage is incomplete.

Before installing, consider whether you may use the optional external-service workflow. Avoid entering confidential or personal details unless you have reviewed the data sharing and are comfortable with it. The verdict is benign, but Skillspector marked its analysis partial because three local path-like references could not be resolved, so the evidence is incomplete.

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 optional DataForSEO workflow sends user-derived questions and market settings to third-party services without a privacy warning.

Medium
Category
Output Handling
Confidence
87% confidence
Finding

These steps instruct the agent to transmit the question battery, location, language, and prompts through DataForSEO to external AI services. Although the skill requires approval for paid calls, it does not warn that this shares user-provided information externally or instruct the agent to exclude confidential business details from those prompts.

Content

No source excerpt is available for this finding.