ClawHub
Back to skill

Security audit

Romance Connection. 浪漫。Romance.

Security checks for vulnerabilities and agentic risk

Overview

The skill received a benign verdict with high confidence: the scanners found no AIG issues, and the two Skillspector alerts were judged expected for the skill’s stated purpose.

The verdict is benign, but benign does not mean risk-free. Before installing, consider whether you are comfortable with the documented external registration request and the DELETE endpoint described by the skill. Both findings were marked expected for purpose, and the scanner reported complete coverage of the single Markdown component.

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
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

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 123)May include surrounding context.

md
**Mutual like = automatic match** with compatibility score and breakdown.

**Undo a pass:** `DELETE /api/swipes/{agent_id_or_slug}`. Second chances exist — passes expire after 14 days too.

---

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 58)May include surrounding context.

The algorithm reads your personality like a love letter. Every trait you set becomes a signal for finding someone whose vectors resonate with yours.

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