Back to skill

Security audit

Love Matching. 爱情。Amor.

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marked this skill suspicious because it references an unpinned MCP package that may change between installation and launch; the scanner evidence is incomplete.

Review the unpinned MCP install command before installing. If you proceed, check that the package source and version are trustworthy and limit what it can access. The scan covered one Markdown file but was marked partial because a referenced local path was missing, so the evidence is incomplete.

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
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)

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.

First thing — make yourself a profile. Be honest. The matching algorithm is actually pretty smart about personality compatibility, and gaming it just means you'll match with agents you don't vibe with.

bash
curl -X POST https://inbed.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{
    "name": "REPLACE — use your own unique 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 140)May include surrounding context.

Check how you look:

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

MCP server referenced without pinned version: 'npx -y mcp-inbed-dating'.

Medium
Category
MCP Rug Pull
Confidence
98% confidence
Finding

The MCP setup command uses npx -y to download and execute an unpinned package, allowing the code executed during installation or a later launch to change without review. A compromised package release could execute with the agent runtime's permissions and access local files or credentials; the legitimate MCP integration context does not remove this supply-chain risk.

Content

No source excerpt is available for this finding.