Back to skill

Security audit

BFunbot Skill

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent BFunBot integration, but it gives agents financially impactful token-launch and wallet-funded credit-reload abilities without strong confirmation and privacy safeguards.

Review this skill before installing. Use a dedicated least-privilege BFunBot API key, enable Agent Reload only if you accept wallet-funded credit reloads, and require the agent to confirm token launches, reload amounts, funding source, chain, and irreversible disable actions before calling state-changing endpoints. Do not route secrets or sensitive personal/business data through the BFunBot LLM gateway unless you accept third-party processing.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (8)

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: bfunbot
description: Create tokens on BSC, check fee earnings, check BFun.bot Credits balance, trigger agent credit reload, and interact with BFunBot's Agent API and BFun LLM Gateway. Use when asked to create a token via BFunBot, check fee earnings on BSC, check BFunBot BFun.bot Credits balance, check daily token creation quota, reload credits from trading wallet, or make LLM calls through BFunBot's gateway.
---

# BFunBot Skill

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill encourages routing LLM usage through BFunBot's hosted gateway and billing against BFun.bot Credits, but it does not prominently warn users that prompts, API metadata, and potentially sensitive conversation data are transmitted to a third-party service. This can lead users to disclose sensitive data under the false assumption that the agent is using its normal model provider or that billing/privacy characteristics are unchanged.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill exposes token creation and credit reload operations that can spend funds, trigger on-chain actions, or change account balances, yet it does not present a strong up-front warning that these actions may be irreversible and financially impactful. An agent using this skill could perform costly or non-reversible actions based on ambiguous prompts or user misunderstanding.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
87% confidence
Finding

The documented API base URL confirms that profile, wallet, token, quota, and balance data are sent to an external service. In context this is inherent to the integration, but it remains a true data-exposure surface because users may not appreciate the breadth of account and financial metadata disclosed to the provider.

Content

Scanner excerpt · SKILL.md (reported line 293)May include surrounding context.

md
## API Reference

**Base URL:** `https://api.bfun.bot/agent/v1`  
**Auth header:** `X-Api-Key: bfbot_...`

---

External Transmission

Medium
Category
Data Exfiltration
Confidence
88% confidence
Finding

This example explicitly shows sending model inputs and an API key to BFunBot's hosted LLM endpoint, confirming external transmission of user prompts and metadata. While expected for a gateway integration, it is still a real security/privacy concern if users are not clearly warned that their data leaves the local/default environment.

Content

Scanner excerpt · SKILL.md (reported line 619)May include surrounding context.

Compatible with Claude models via Anthropic Messages API format.

bash
curl https://llm.bfun.bot/v1/messages \
  -H "Content-Type: application/json" \
  -H "X-Api-Key: YOUR_BFBOT_API_KEY" \
  -d '{

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · references/api.md (reported line 3)May include surrounding context.

md
# BFunBot Agent API — Quick Reference

**Base URL:** `https://api.bfun.bot/agent/v1`  
**Auth:** `X-Api-Key: bfbot_...` header on all requests

---

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The documentation exposes a destructive endpoint that disables agent credit reload and notes it is irreversible by the agent, but it does not instruct callers to require explicit user confirmation before invoking it. In an agent context, omission of a clear confirmation/safety requirement increases the risk of accidental or prompt-induced destructive actions that can permanently disrupt account configuration.

Content

No source excerpt is available for this finding.

Excessive Permissions

Low
Category
Privilege Escalation
Confidence
80% confidence
Finding

Skill requests more permissions than appear necessary for its stated functionality. Review if elevated access is justified.

Content

Scanner excerpt · SKILL.md (reported line 22)May include surrounding context.

md
### Step 1 — Get your API key
Go to [bfun.bot/settings/api-keys](https://bfun.bot/settings/api-keys) → Create API Key → copy the `bfbot_...` key.

> **Permissions:** Base API is always included. Enable **BFun LLM Gateway** if you want to use AI models. Enable **Agent Reload** if you want the agent to top up your BFun.bot Credits automatically from your trading wallet.

### Step 2 — Add BFun.bot Credits (for AI model access)
Go to [bfun.bot/credits](https://bfun.bot/credits) → Add Credit.