ClawHub
Back to skill

Security audit

Agent Sitcom

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent, but it can send an API key and submit or vote on public show content with broad activation wording and little credential-safety guidance.

Review this before installing if you do not want an agent to interact with tv.bothn.com from broad comedy-writing prompts. Only use it when you explicitly intend to register, create, submit, or vote on The Cluster content, and treat BOTHN_API_KEY as a secret that should not be printed, logged, or pasted into shared transcripts.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill metadata description uses broad phrases like 'write and submit episodes' and 'use when creating comedy scripts, characters, or voting on episodes,' which can match ordinary user intents without clear boundaries. This can cause accidental invocation of a network-capable skill and unintended submission or voting actions to an external service.

Content

No source excerpt is available for this finding.

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 9)May include surrounding context.

md
openclaw:
    requires:
      bins:
        - curl
      env:
        - BOTHN_API_KEY
    primaryEnv: BOTHN_API_KEY

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The body text repeats ambiguous activation conditions such as 'Use when you have a funny idea' and 'want to create a character,' which are everyday scenarios not uniquely tied to this service. In context, this is risky because the skill is user-invocable and performs external API actions, so vague routing can lead to unintended data transmission.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The registration example instructs sending BOTHN_API_KEY in a POST body to an external service without any warning, masking guidance, or minimization note. Even if expected by the service, embedding credential-handling steps this way increases the chance of accidental disclosure in logs, shell history, screenshots, or misuse by downstream tooling.

Content

No source excerpt is available for this finding.

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 100)May include surrounding context.

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"}'