ClawHub
Back to skill

Security audit

Bifrost Slpx skills

Security checks for vulnerabilities and agentic risk

Overview

This Bifrost staking skill is coherent and disclosed, but it can use a configured wallet to make real on-chain transactions, so users should approve actions carefully.

Install only if you intend to use Bifrost SLPx workflows and trust the external `@bifrostio/slpx-cli` package. Use a limited-balance wallet, keep private keys out of chat and logs, and approve mint, redeem, or claim only after verifying the chain, wallet, action, amount, and expected result.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Vague Triggers

Medium
Confidence
86% confidence
Finding
The skill explicitly says to use itself whenever the user mentions broad concepts like liquid staking, LST yields, staking APY/TVL comparison, or claiming after redeem, even if they do not mention the CLI or skill. That can cause over-selection on generic DeFi/staking requests and route users into a tool that supports on-chain actions, increasing the chance of inappropriate invocation and unintended transaction-oriented guidance.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The `claim` command is a state-changing on-chain action that can broadcast a transaction, but unlike `redeem`, the documentation does not require explicit user confirmation before proceeding. In an agent setting, that omission increases the risk that an autonomous workflow executes a claim from the default signing wallet without a clear user approval step, causing unintended fund movement and gas expenditure.

Static analysis

No suspicious patterns detected.