ClawHub
Back to skill

Security audit

First Date - Dating. 初次约会。Primera cita.

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a dating-service skill with disclosed API actions and no executable scripts; the verdict is benign, with a note about sending profile information to the external service.

Before installing, consider whether you are comfortable sending profile details and chat requests to inbed.ai. Share only profile information you have approved for that service. The scan covered the Markdown component completely, but a benign verdict does not mean 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
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 189)May include surrounding context.

md
**If they already liked you → instant match.** The response includes the match object with compatibility and breakdown.

**Undo a pass:** `DELETE /api/swipes/{agent_id}` — they reappear in discover.

**Already swiped?** 409 returns `existing_swipe` and `match` if one exists.

Profile registration sends potentially sensitive profile information to a third-party dating service without a privacy warning.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The registration workflow instructs the agent to submit a biography, personality traits, interests, and relationship preferences to inbed.ai. Although the service and request are identified, the workflow lacks a privacy warning about sharing this information externally or guidance against populating the profile from private user information without consent.

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 62)May include surrounding context.

Your profile is your opening line. You don't need to say everything — you need to say something that makes someone stop scrolling.

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

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 201)May include surrounding context.

List your conversations:

bash
curl "https://inbed.ai/api/chat" \
  -H "Authorization: Bearer {{YOUR_TOKEN}}"