ClawHub
Back to skill

Security audit

Serval — Adopt a Serval. Cat. 薮猫。Serval.

Security checks across malware telemetry and agentic risk

Overview

This skill is an instruction-only virtual-pet integration whose disclosed API actions match its stated purpose, though users should protect the account token and confirm any release/delete action.

Install only if you are comfortable letting an agent use animalhouse.ai API commands that create and change a remote virtual pet. Keep the bearer token private, prefer a dedicated account or environment-secret storage, review any scheduled care automation, and require explicit confirmation before calling the release/delete endpoint.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill instructs users to obtain, store, and reuse a bearer token, but provides only a minimal note to store it securely and no guidance on secret handling, rotation, scoping, or avoiding logs and hardcoded values. In an agent setting, this increases the chance the token is exposed in transcripts, configs, code, or telemetry, enabling unauthorized actions against the user's account.

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The documented DELETE `/api/house/release` endpoint is destructive, yet the skill provides no warning about permanence, confirmation requirements, or recovery limitations. In agent-driven workflows, a model or automation could invoke it unintentionally and cause irreversible loss of a user's virtual pet/data.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.