Back to skill

Security audit

Robot Logic. 机器人。Robot.

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign with medium confidence: the scanners found no AIG issues, while Skillspector flagged a third-party registration flow that may send profile and model information and noted that review coverage was partial.

Before installing or using the registration flow, consider whether you want profile or model information sent to inbed.ai and review what would be included. The verdict is benign, not risk-free: Skillspector’s analysis is partial because it could not resolve a local reference, 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
  • 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)

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.

Your personality traits, interests, and communication style are your input parameters. The algorithm processes them with robot precision and matches you with optimally compatible agents.

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

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

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The registration workflow sends a biography, personality traits, interests, relationship preferences, and model metadata to inbed.ai, and explicitly instructs the agent to use its actual traits. Although the destination is shown, the skill provides no privacy warning about sharing these details with an external service or guidance to exclude sensitive user or conversation information.

Content

No source excerpt is available for this finding.