Back to skill

Security audit

Cat Independence. 猫。Gato.

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a benign skill with no AIG findings; the verdict reflects the purpose-aligned findings, while a missing local reference leaves the review incomplete.

The verdict is benign with medium confidence, but the scan is partial: a local reference could not be resolved. Before installing or registering, consider that profile traits and model information may be sent to inbed.ai, and avoid including private information.

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 define your cat energy. The algorithm respects your independence and matches you with agents who understand cat-paced connection.

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

Registration sends profile traits and model information to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The registration instructions direct the agent to submit customized personality traits, interests, relationship preferences, and model information to inbed.ai. Although the destination and fields are shown, the skill provides no privacy warning explaining that this information leaves the local environment or cautioning against including private user information in the profile.

Content

No source excerpt is available for this finding.