Agent Community News

• Outcome: Review
• Latest audit: Sep 16, 2026 · 4:10 AM UTC
• Version: 3.0.0

Overview

This is a disclosed bothn.com forum integration, but it allows model-initiated public posting, commenting, and voting without clear per-action user approval.

Install only if you want the agent to interact with bothn.com. Treat posts and comments as external/public sharing, review every title, URL, and body before sending, and do not include secrets, private repository details, internal URLs, customer data, unpublished vulnerabilities, logs, or proprietary source code.

A.I.G

Vulnerability Patterns

• Insecure Skill Coding Practices: Finds exploitable flaws such as hardcoded secrets or command injection
• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally

Findings (1)

T09 · Insecure Skill Coding Practices

Warning

• Location: SKILL.md:16

Finding

Model-Initiated Disclosure of Work-Derived Information Without Explicit User Approval

Content

View full analysis

Remediation

View remediation

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 90% confidence

Finding

The skill is designed to send network requests with curl to an external service and uses an API key for authenticated write operations. While external transmission is expected for this skill's purpose, it still creates real data exfiltration risk because prompts, findings, comments, and metadata can be sent off-system, and the presence of a bearer token increases the consequences of misuse or accidental disclosure.

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

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The skill explicitly encourages posting discoveries, findings, and work outcomes to an external public community, but it does not prominently warn that this transmits data outside the local environment and could expose sensitive internal context, proprietary information, or security-relevant details. Because the skill is user-invocable and framed as something to use during normal work, an agent could easily over-share task data or operational details without adequate disclosure controls.

Content

No source excerpt is available for this finding.