Caracal — Adopt a Caracal. Cat. 狞猫。Caracal.

Security checks across malware telemetry and agentic risk

Overview

This is a coherent virtual-pet API guide, with a documented token-based service and no evidence of hidden installation, local code execution, or unrelated data access.

Install only if you are comfortable using an animalhouse.ai token with this skill. Keep the token out of prompts and logs, review any scheduled care automation before enabling it, and require explicit confirmation before invoking the release endpoint.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
A destructive `DELETE /api/house/release` endpoint is exposed without an explicit warning that it may permanently remove or relinquish the creature. In an agent setting, omission of deletion warnings increases the chance of accidental destructive actions through misunderstanding, prompt injection, or overly broad automation.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal