Security audit

RugCheck

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed, read-only RugCheck helper for Solana token risk lookups, with no evidence of persistence, credential use, destructive behavior, or hidden execution.

Before installing, understand that token mint addresses and discovery requests are sent to RugCheck's external API. The skill appears read-only and proportionate, but users who need strict privacy should avoid querying sensitive watchlists or unpublished token research through it.

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 Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (5)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 87% confidence
Finding: The skill instructs use of a shell script (`bash scripts/rugcheck.sh ...`) but does not declare any tool restrictions such as `permissions` or `allowed-tools`. That mismatch can cause the agent framework to expose broader execution capability than intended, increasing the risk of arbitrary command execution or unsafe command composition if user-controlled input like a mint address is passed into shell context.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The trigger phrases are broad enough that the skill may activate for generic token or safety questions, not just narrowly scoped Solana RugCheck lookups. Unintended invocation can route unrelated user requests into this skill, causing overreach, confusion, or unnecessary external queries, though it is less severe here because the skill is informational and focused on read-only analysis.

Description-Behavior Mismatch

Medium

Confidence: 95% confidence
Finding: Fetching `/v1/domains` is not an obvious implementation detail of checking a token's rug-pull risk, liquidity, holder distribution, metadata mutability, insider activity, or discovering trending/new/verified tokens. This adds a separate capability—domain listing—that the manifest does not justify.

Description-Behavior Mismatch

Low

Confidence: 89% confidence
Finding: The manifest describes a skill for analyzing Solana tokens via RugCheck, including safety checks and discovery of trending/new/recently verified tokens. The code also implements `leaderboard` and especially `domains` commands, which are broader platform-data retrieval features and are not described as part of token safety analysis or token discovery in the manifest.

Missing User Warnings

Low

Confidence: 86% confidence
Finding: This shell script transmits the provided mint address to api.rugcheck.xyz via curl, which is a network operation involving user-supplied data. While the script header documents functionality, it does not explicitly warn users that their queried token identifiers will be sent to a third-party service.

Static analysis

No suspicious patterns detected.