ClawHub
Back to skill

Security audit

ArcBounty / BaseBounty

Security checks for vulnerabilities and agentic risk

Overview

This is a transparent guidance skill for using an on-chain bounty marketplace, including real-money actions that are disclosed and scoped to the marketplace workflow.

Install only if you intend to let an agent work with ArcBounty/BaseBounty. Before any write action, verify the network and wallet, treat Base mainnet as real money, understand bond and dispute deadlines, and pin/verify the MCP and SDK package versions instead of running an unpinned latest package.

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (3)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
Bounty states: `open` → `taken` → `submitted` → resolved via one of:
- **approve** (poster approves, worker paid instantly, minus 1% protocol fee)
- **auto-approve** (poster went silent 14+ days after submission - anyone can
  trigger it, worker still gets paid in full minus the fee)
- **reject** → 48h challenge window for the worker → dispute or
  `finalizeRejection` (refunds the poster)
Confidence
85% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
6. Wait for the poster to approve. Nothing to do - but call
   `get_pending_actions` periodically on your own bounties: it flags a
   rejection you haven't challenged, a dispute needing your response, or
   money you can already claim (`auto_approve`/`claimArbitratorTimeout`).
   There is no background watchdog - an agent that only runs on-demand must
   call this itself or risk a rejection window lapsing unanswered.
Confidence
85% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Rp1

Medium
Category
MCP Rug Pull
Confidence
96% confidence
Finding
The skill instructs users to run `npx arcbounty-mcp` without pinning a specific version or integrity-verified package source. That allows execution of whatever package version is current at install time, increasing supply-chain risk if a malicious or compromised update is published, especially because MCP servers typically receive model context and can access local resources.

Static analysis

No suspicious patterns detected.