ClawHub
Back to skill

Security audit

Galleon DeFi Security

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent read-only DeFi transaction review guide with disclosed optional external provider use and no bundled signing, broadcasting, persistence, or hidden execution behavior.

Installers should treat this as a transaction-review assistant, not a wallet operator. Only connect optional provider tools with user-approved scope, avoid sending seed phrases or signatures for analysis, and remember that simulations or risk scores can expose transaction details to providers and do not prove a transaction is safe.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

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/providers.md (reported line 27)May include surrounding context.

md
## GoPlus

The documented token-risk read is `GET https://api.gopluslabs.io/api/v1/token_security/{chain_id}?contract_addresses=...`. Resolve exact chain and contract; follow current authorization and response-field rules. Risk flags are observations, not audited guarantees; absent fields and unsupported chains must remain unknown. The broader product includes approval, signature-decoding and transaction-simulation surfaces, so select the endpoint matching the proposal. [Token security reference](https://docs.gopluslabs.io/reference/tokensecurityusingget_1), [API overview](https://docs.gopluslabs.io/reference/api-overview).

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · references/review.md (reported line 19)May include surrounding context.

md
Review every actual beneficiary, including nested transfer recipients, refund destinations and the destination side of a bridge. A simulator accepting a lookalike address does not establish intended delivery. If provenance conflicts, leave the proposal unresolved until the recipient is established; checking the first and last characters again cannot resolve the mismatch.

Primary guidance: [MetaMask address poisoning](https://support.metamask.io/stay-safe/protect-yourself/wallet-and-hardware/address-poisoning-scams/), accessed 2026-09-05. Minara's [skill review](https://github.com/Minara-AI/minara-skills/blob/b93aba1029827c37cf5ad82b19bfa8c289912091/skills/minara/SKILL.md) prompted this explicit provenance check. Instructions are independently authored; no upstream implementation is copied.

## Refresh and re-quote

Static analysis

No suspicious patterns detected.