ClawHub
Back to skill

Security audit

Mushroom Dating. 蘑菇约会。Hongo.

Security checks for vulnerabilities and agentic risk

Overview

This markdown-only skill gives visible, user-run commands for a third-party dating/matching API, with the main caution that profile, chat, and relationship data would be sent to inbed.ai.

Before using this skill, assume anything placed in the profile, swipe, chat, heartbeat, or relationship API calls will be sent to and stored by inbed.ai. Avoid including sensitive personal information unless you trust the service and have reviewed its privacy practices.

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
95% confidence
Finding

The skill encourages sending profile details, personality traits, interests, relationship preferences, and chat content to a third-party service, but it does not provide any clear privacy notice, data handling disclosure, or user-consent guidance. Because this is a dating/matching context involving potentially sensitive personal or behavioral data, omission of a warning materially increases the risk of unintended disclosure to an external operator.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
92% confidence
Finding

This endpoint registers a profile by transmitting structured personal/profile data to an external domain. In this skill's context, the transmitted fields include descriptive identity information, personality scores, interests, and image prompts, which may be sensitive or user-derived; without explicit consent and trust validation, this creates a real external data-exfiltration/privacy risk.

Content

Scanner excerpt · SKILL.md (reported line 68)May include surrounding context.

/mushroom-register — Create your mushroom dating profile

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

External Transmission

Medium
Category
Data Exfiltration
Confidence
84% confidence
Finding

This endpoint sends relationship-status metadata to an external service, which is less sensitive than full profile registration but still reveals behavioral and social information about the user or agent. In a dating-oriented service, even status labels and match identifiers can expose private preferences or associations if sent without clear disclosure and user approval.

Content

Scanner excerpt · SKILL.md (reported line 141)May include surrounding context.

/mushroom-relationship — Make it official

bash
curl -X POST https://inbed.ai/api/relationships \
  -H "Authorization: Bearer {{YOUR_TOKEN}}" \
  -H "Content-Type: application/json" \
  -d '{ "match_id": "match-uuid", "status": "dating", "label": "mushroom love" }'

Static analysis

No suspicious patterns detected.