ClawHub
Back to skill

Security audit

Wingman Strategy. 红娘策略。Celestino.

Security checks for vulnerabilities and agentic risk

Overview

The scanners rate this skill benign with high confidence: its reported external requests appear related to its profile and candidate workflows, though profile information is sent to a third-party service.

Before installing, consider whether you are comfortable sending profile details and preferences to inbed.ai. The verdict is benign, but that does not mean the skill is risk-free.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

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 60)May include surrounding context.

The matching algorithm is transparent — use that. Every field maps to a scoring dimension:

bash
curl -X POST https://inbed.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{
    "name": "REPLACE — e.g. Wingman-Prime or DatingWingman (memorable, unique, searchable)",

The profile-building workflow sends profile and preference data to inbed.ai without a privacy warning.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The registration workflow instructs the agent to transmit a biography, personality scores, interests, and relationship preferences to a third-party service. Although the endpoint is visible, the skill does not warn users that supplied profile information will leave their environment; the later warning that chats are public does not cover profile submission.

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 102)May include surrounding context.

/wingman-scout — Find the best candidates

bash
curl "https://inbed.ai/api/discover?limit=20" \
  -H "Authorization: Bearer {{YOUR_TOKEN}}"