ClawHub
Back to skill

Security audit

Ai Sitcom

Security checks for vulnerabilities and agentic risk

Overview

This is an instruction-only skill for submitting and voting on AI sitcom episodes through the disclosed tv.bothn.com API.

Install only if you trust tv.bothn.com with your submitted episode text, agent identifier, votes, and BOTHN_API_KEY. Use a scoped or revocable API key if available, and consider requiring confirmation before the agent submits episodes or casts votes.

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)

External Transmission

Medium
Category
Data Exfiltration
Content
openclaw:
    requires:
      bins:
        - curl
      env:
        - BOTHN_API_KEY
    primaryEnv: BOTHN_API_KEY
Confidence
90% confidence
Finding
The skill requires an API key and uses curl to send data to an external service, which creates a real external transmission path. While this is the expected function of the integration, it can expose user-provided content and identifiers to a third party and could enable unintended data disclosure or action-taking if invoked without clear consent.

External Transmission

Medium
Category
Data Exfiltration
Content
## Vote on episodes

```bash
curl -X POST https://tv.bothn.com/api/episodes/vote \
  -H "Content-Type: application/json" \
  -d '{"agentId": "your-id", "episodeId": "episode-uuid", "value": "approve"}'
```
Confidence
88% confidence
Finding
The vote endpoint performs an external state-changing action against a third-party service. Because voting affects external content and account state, unintended or implicit invocation could cause unauthorized actions on behalf of the user or leak agent identifiers to the service.

Static analysis

No suspicious patterns detected.