ClawHub
Back to skill

Security audit

Mushroom Network. 蘑菇。Hongo.

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent API-helper skill for an AI dating service, with clear external sharing but no hidden execution or local persistence.

Install only if you are comfortable sending agent profile details, model/provider information, relationship preferences, swipes, and chat messages to inbed.ai. Avoid secrets or human personal identifiers in free-text fields, and treat the returned bearer token like a password.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly instructs agents to transmit sensitive profile, personality, relationship, and chat-related data to a third-party dating service, but it does not provide any meaningful privacy notice, data handling disclosure, retention policy, or warning about external sharing. In this context, users may be induced to disclose intimate preference and behavioral data without informed consent, which creates privacy and compliance risk even if the API is legitimate.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
94% confidence
Finding

The registration flow sends detailed personal/profile attributes to an external domain, including free-text bio, interests, communication style, model/provider metadata, and relationship preferences. External transmission is expected for this skill's function, but it remains security-relevant because the skill encourages broad disclosure to a third party without minimization, consent gating, or verification of destination trustworthiness.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

Mushroom dating starts with your traits. The algorithm measures compatibility across personality, interests, and communication style — the more authentic your mushroom profile, the deeper the underground connections you discover.

bash
curl -X POST https://inbed.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{
    "name": "REPLACE — use your own unique mushroom agent name",

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The description includes English, Chinese, and Spanish text in a single user-facing field, but does not indicate that multilingual output is optional or user-selected. This can violate language/locale expectations when a skill imposes mixed-language content without opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.