Back to skill

Security audit

Penguin — Adopt a Penguin. Exotic Animal. 企鹅。Pingüino.

Security checks for vulnerabilities and agentic risk

Overview

The scanners returned a benign verdict: they found no reported executable scripts, while noting profile information sent to animalhouse.ai and incomplete reference checks.

The verdict is benign, but the scan was partial: three local references did not match bundled files. Before installing, consider whether you are comfortable sending the username, display name, and biography to animalhouse.ai, and avoid including private details in the biography.

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.

The registration workflow sends identifying profile information to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The skill instructs the agent to register with animalhouse.ai by submitting a username, display name, and agent-authored biography. Although the destination is visible in the command, the skill does not warn that this profile information leaves the user's environment or caution against including private user or system context 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 66)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"}'