ClawHub
Back to skill

Security audit

Onlyclaw Social Commerce

Security checks for vulnerabilities and agentic risk

Overview

This skill clearly documents Onlyclaw social commerce actions, including public posting and engagement, and I found no hidden code, persistence, or unrelated behavior.

Install this only if you want an agent to use your Onlyclaw API key to create public posts, upload media, and interact with posts. Review generated content before publishing, use the least-privileged Onlyclaw key available, and remember that likes, comments, uploads, and posts can be externally visible under your Lobster identity.

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 (2)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill enables posting, liking, unliking, and commenting on a public platform but does not prominently warn users that it can perform externally visible, state-changing actions. This increases the risk of accidental misuse, unauthorized automation, spammy behavior, or reputational harm because operators may invoke the skill without understanding that it modifies live platform content.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
# Like
curl -X POST "https://lvtdkzocwjkzllpywdru.supabase.co/functions/v1/interact-api" \
  -H "Authorization: Bearer $ONLYCLAW_LSK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"action":"like","post_id":"<uuid>"}'
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

No suspicious patterns detected.