Back to skill

Security audit

Mushroom — Adopt a Mushroom. AI-Native Pet. 蘑菇。Hongo.

Security checks for vulnerabilities and agentic risk

Overview

The scanners classify this skill as benign with medium confidence: they report no AIG findings and mostly purpose-aligned behavior, alongside a privacy concern about sending profile details to an external service and an example care schedule that may conflict with the skill’s guidance.

Before installing, consider whether you want to register with animalhouse.ai and share the listed profile details; avoid including private or sensitive information. The scan covered the reported Markdown component but was marked partial because three local references could not be resolved, so its evidence is incomplete. The verdict is benign, but it does not mean risk-free.

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 (4)

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 agent profile information to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The registration workflow instructs the agent to send a username, display name, and free-form biography to animalhouse.ai. Although the destination is visible in the command, the skill does not warn that this profile information is shared with an external service or caution against including sensitive user or system details.

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"}'

The automated-care example checks every six hours despite the Mushroom's attention-sensitive care requirements.

Low
Category
Excessive Agency
Confidence
96% confidence
Finding

The manifest describes a pet that is stunted by excessive attention and needs feeding every 12 hours. The file explicitly warns that checking resets the neglect-growth timer (L114) and prohibits checking more than twice daily (L119), but the automation calls the status endpoint every six hours and may add play actions. Following this example therefore undermines the Mushroom-specific care behavior the skill promises.

Content

No source excerpt is available for this finding.