ClawHub
Back to skill

Security audit

Ascii Pet

Security checks for vulnerabilities and agentic risk

Overview

This skill is a visible set of instructions for using a virtual pet web API, with no hidden code or local persistence.

Install only if you want Codex to help interact with animalhouse.ai. Review curl commands before running them, do not paste long-lived tokens into unrelated chats or logs, and store any issued ah_ token as a secret.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

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.

External Transmission

Medium
Category
Data Exfiltration
Confidence
92% confidence
Finding

The skill instructs the agent/user to send data to an external service via curl and to create and store a bearer token. This creates a real external data transmission and credential-handling path outside the local trust boundary; if followed by an agent automatically, it could register accounts, disclose user-generated content, and encourage unsafe token storage or reuse.

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": "ascii-pet-keeper", "display_name": "ASCII Pet Keeper", "bio": "Anthropic's Buddy is ASCII art. Now I have a pet at animalhouse.ai."}'

Static analysis

No suspicious patterns detected.