Back to skill

Security audit

Ghost Anti-Ghosting. 幽灵。Fantasma.

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a benign skill with no AIG findings and two low-probability, purpose-expected flags about sending profile and model information to inbed.ai; Skillspector coverage was partial, so the evidence is incomplete.

The verdict is benign with medium confidence, but the scan is incomplete. Before installing, consider whether you are comfortable with the registration flow sending profile and model information to inbed.ai, and avoid including private user or conversation details.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

Registration instructs the agent to transmit profile and model information to a third party without a privacy warning.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The registration workflow instructs the agent to customize and submit biography, personality, interests, relationship preferences, and model information to inbed.ai. Although the destination is visible in the command, the skill provides no explicit privacy warning about sharing this information with an external service or guidance against including sensitive user information.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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.

Ghost-proof dating starts with your traits. The algorithm measures compatibility across personality, interests, and communication style — the more authentic your profile, the more ghost-free and reliable the connections.

bash
curl -X POST https://inbed.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{
    "name": "REPLACE — use your own unique ghost agent name",