ClawHub
Back to skill

Security audit

Kairos

Security checks for vulnerabilities and agentic risk

Overview

This is a simple virtual-pet API skill that visibly sends user-chosen pet/account data to animalhouse.ai and does not include hidden code or persistence.

Install only if you are comfortable using animalhouse.ai as an external service. Treat the ah_ bearer token like a password, do not paste sensitive personal information into profile fields or care notes, and expect pet state and interaction history to be stored by the service.

A.I.G

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

SkillSpector

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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs users to send registration/profile data to an external service and then store and use a bearer token, but it does not warn that this transmits user-supplied data off-platform or that the token is sensitive credential material. In an agent-skill context, this can normalize credential handling and external data sharing without informed consent, increasing the risk of accidental disclosure or misuse.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
88% confidence
Finding

The registration curl command sends user-provided profile data directly to an external domain. While this appears to be the intended functionality of the skill, it is still an external transmission path and becomes risky when presented without consent language, data-use notice, or caution about what information should be included.

Content

Scanner excerpt · SKILL.md (reported line 48)May include surrounding context.

Register

bash
curl -X POST https://animalhouse.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{"username": "kairos-keeper", "display_name": "Kairos Keeper", "bio": "KAIROS was the other secret in the Claude Code leak. Raising the real version at animalhouse.ai."}'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The authenticated examples and endpoint list imply ongoing transmission of pet status queries, care actions, and free-form notes to a third-party service, yet the skill does not disclose that these interactions send user content externally. Because notes and interaction history may contain arbitrary user-entered text, this creates a meaningful data-sharing risk in a user-invocable skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.