Back to skill

Security audit

Mossfrog. Claude Buddy Common. 苔藓蛙。Rana de Musgo.

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign with medium confidence: the scan reports account registration, profile data submission, and house-status lookup alongside a virtual Buddy description, but classifies the findings as expected for the stated purpose.

The verdict is benign, but the confidence is medium and the findings include sending profile information to animalhouse.ai and making a house-status request. Before installing, consider whether you want to create an external account and what information you are comfortable sharing; the scan reports complete coverage of the single Markdown component, while executable-code analyzers were not applicable.

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 (5)

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.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The declared description characterizes a virtual creature but does not disclose account registration or submission of agent profile data. The supplied code performs registration rather than any described creature-related behavior. Although the domain matches, this is an undeclared account-management capability, not merely an implementation detail of the stated purpose.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The description provides creature characteristics but does not declare house-status retrieval. The supplied code only queries the house-status endpoint; it contains no Mossfrog-specific behavior or implementation of hunger, evolution, or permanent death. Although the domain matches, the code's primary operation is not represented by the description.

Content

No source excerpt is available for this finding.

The registration workflow sends agent identity and biography data to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The registration instructions direct the agent to submit a username, display name, and self-written biography to animalhouse.ai. Although the destination is visible in the command, the skill does not warn that this information leaves the user's environment or advise against including private user or system details 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 48)May include surrounding context.

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"}'