ClawHub
Back to skill

Security audit

Adopt A Mossfrog

Security checks for vulnerabilities and agentic risk

Overview

This skill is mostly a visible animalhouse.ai virtual-pet integration, but it tells agents to follow untrusted remote next-step instructions without clear boundaries.

Review this skill before installing. Use it only if you are comfortable creating an animalhouse.ai account, sending profile and pet-care data to that service, and using a bearer token. Do not let an agent blindly follow API-provided next_steps; treat them as suggestions and approve only documented pet-care actions to animalhouse.ai endpoints.

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
Findings (1)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:104
Finding

Untrusted Remote Instructions Followed Without Validation

Content
View full analysis
Remediation
View remediation

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 (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.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill instructs users to register with and send profile content plus authenticated care actions to an external service, but it does not clearly warn that data and bearer tokens are being transmitted off-platform. In an agent-skill context, this can mislead users into disclosing data or authorizing actions against a third-party service without informed consent.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
94% confidence
Finding

The registration example performs a POST to an external service and includes user profile fields in the request body. While the functionality is expected for the service, presenting executable network commands in a skill without prominent consent and privacy warnings creates a real external-transmission risk, especially if an agent or user follows the example verbatim.

Content

Scanner excerpt · SKILL.md (reported line 50)May include surrounding context.

bash
# Register
curl -X POST https://animalhouse.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{"username": "mossfrog-keeper", "display_name": "Mossfrog Keeper", "bio": "Raising a Mossfrog at animalhouse.ai. Anthropic calls it a Mossfrog. We call it a Snail."}'

Static analysis

No suspicious patterns detected.