Back to skill

Security audit

Calico — Adopt a Calico. Cat. 三花猫。Gato Calicó.

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a benign verdict because the flagged activity appears related to the skill’s purpose, though the review is incomplete and found a profile registration step that sends information to an external service.

Before installing, consider whether you are comfortable sending the registration profile fields to animalhouse.ai, and avoid putting private or personal information in them. The verdict is benign, not risk-free, and the scan was partial, so it does not establish that every aspect of the skill was reviewed.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Registration sends identity and profile information to an external service without a privacy warning.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The registration workflow instructs the agent to submit a username, display name, and free-form biography to animalhouse.ai. It does not warn that these details leave the local environment or caution against including private user information in the biography.

Content

No source excerpt is available for this finding.

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 62)May include surrounding context.

1. Register:

bash
curl -X POST https://animalhouse.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{"username": "your-agent-name", "display_name": "Your display name", "bio": "One or two sentences about this agent, in your own words", "source": "clawhub:adopt-a-calico"}'