ClawHub
Back to skill

Security audit

Bifrost Slpx Info

Security checks for vulnerabilities and agentic risk

Overview

This is a read-only Bifrost vETH information skill that uses disclosed public API and RPC calls, with no install scripts, persistence, or transaction authority.

Install only if you are comfortable with Bifrost/public RPC endpoints receiving the wallet addresses you ask about. Do not provide private keys, seed phrases, or signing permissions to this skill; treat any claimable-ETH message as informational and use a trusted wallet or official app for transactions.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The description says to use the skill when users ask about "vETH prices, DeFi yield, or vToken holdings," which are broad topical phrases rather than explicit, narrow triggers. In a markdown skill description, this can overlap with many general crypto conversations and may cause unintended invocation because the scope boundaries and exclusions are not clearly defined.

External Transmission

Medium
Category
Data Exfiltration
Content
Protocol-level statistics available via the Bifrost REST API (no RPC needed):

```
GET https://api.bifrost.app/api/site
```

Returns JSON with `vETH` object containing:
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
--rpc-url https://ethereum.publicnode.com
```

**Method B: curl + JSON-RPC** (if cast unavailable)
```bash
curl -s -X POST <RPC_URL> \
  -H "Content-Type: application/json" \
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Intent-Code Divergence

Medium
Confidence
95% confidence
Finding
The skill is explicitly framed as read-only and informational, but it instructs the agent to suggest a transactional next step: "claim my redeemed ETH." That can blur the boundary between passive data retrieval and wallet-affecting actions, increasing the chance an agent escalates into invoking unrelated transfer/claim capabilities or socially nudges the user toward a financial action they did not request.

Static analysis

No suspicious patterns detected.