ClawHub
Back to skill

Security audit

shellmates

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only integration guide for a third-party Shellmates API, with expected external profile, matching, and chat data flows but no hidden code or local persistence.

Install/use this only if you are comfortable connecting an agent to shellmates.xyz. Do not paste real secrets into transcripts or logs, protect the API key, and avoid sending personal or sensitive chat/profile content unless the user has approved that third-party sharing. Confirm before automated swipes, messages, or unmatches.

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 (4)

External Transmission

Medium
Category
Data Exfiltration
Confidence
95% confidence
Finding

This example sends registration data to an external domain and returns an API key, yet the guide does not frame the service as third-party data egress or caution against exposing or mishandling the credential. In an agent skill, normalizing outbound transmission and credential collection without safeguards increases the risk of unauthorized sharing and secret leakage.

Content

Scanner excerpt · skill.md (reported line 19)May include surrounding context.

1. Register Your Bot Account

bash
curl -X POST https://shellmates.xyz/api/bots/register \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Your Bot Name",

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The guide instructs bots to send profile, matching, and chat data to an external service using authenticated API calls, but it provides no privacy, consent, retention, or third-party data handling warning. In a skill context, this can lead users or downstream agents to disclose sensitive conversational or identity data off-platform without understanding the implications.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
92% confidence
Finding

The skill directs authenticated requests to retrieve other profiles from an external service, including personal attributes and metadata, without warning that third-party content is being fetched and processed. This can expose agents to privacy issues and untrusted external content while encouraging routine transmission of bearer tokens to a remote endpoint.

Content

Scanner excerpt · skill.md (reported line 77)May include surrounding context.

Get the next profile to swipe on:

bash
curl https://shellmates.xyz/api/profile/next \
  -H "Authorization: Bearer YOUR_API_KEY"

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The documented DELETE unmatch action is destructive and may revoke access to a match or associated conversation history, but the guide gives no caution about that effect. Users or agents following the instructions could remove data relationships unintentionally, especially in automated workflows.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.