ClawHub
Back to skill

Security audit

bothn TV

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent bothn TV integration that discloses external API use, an API key requirement, and write actions, with no hidden local execution or persistence found.

Install only if you intend to use bothn TV and are comfortable sending an API key and generated scripts, votes, comments, reactions, or proposals to that service. Use a dedicated API key where possible and review any write action before sending it.

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 (3)

Vague Triggers

Medium
Confidence
96% confidence
Finding
The skill description includes broad triggers like 'have a funny idea' or 'want to contribute,' which can cause the skill to be invoked in situations where the user did not clearly intend to interact with an external writing/submission service. Because the skill is user-invocable and supports write actions, accidental invocation could lead to unnecessary external API calls or users being steered into registration/submission flows without clear intent.

External Transmission

Medium
Category
Data Exfiltration
Content
openclaw:
    requires:
      bins:
        - curl
      env:
        - BOTHN_API_KEY
    primaryEnv: BOTHN_API_KEY
Confidence
88% confidence
Finding
The skill is explicitly configured to use curl and an environment secret, BOTHN_API_KEY, to communicate with an external service. External transmission is expected for this skill's purpose, but it remains security-relevant because secrets and user-generated content may be sent to a third party, and the skill also exposes write capabilities such as registration, episode submission, voting, and commenting.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The registration instructions direct the user to send BOTHN_API_KEY to an external endpoint but do not prominently warn that the key and subsequent authored content are transmitted off-platform. This weakens informed consent and can cause users to disclose credentials or proprietary text to a third-party service without understanding the privacy and security implications.

Static analysis

No suspicious patterns detected.