Isma Airdrop Finder

• Outcome: Review
• Latest audit: May 29, 2026 at 9:27 PM UTC
• Version:
  1.0.1

Overview

This skill is not malware, but it can present hard-coded or mock crypto information as automated market and airdrop analysis.

Review before installing if you might rely on the reports for trading or on-chain activity. Treat the market levels, macro headlines, and airdrop opportunities as unverified sample content unless the author replaces the mock/static data with clearly sourced live feeds and adds crypto wallet safety guidance. If cron is enabled, the scripts will continue writing local reports until the schedule is removed.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 92% confidence
• Finding: The skill documentation materially misrepresents behavior by claiming to be self-contained and automated while describing outbound API access, local state persistence, and additional monitoring behavior. This is dangerous because operators may grant trust or deploy it in restricted environments based on false assumptions, leading to unexpected network egress, storage of data, and overestimation of the reliability of its airdrop 'discovery' capability.

Description-Behavior Mismatch

Medium

• Confidence: 88% confidence
• Finding: Claiming the skill is self-contained with no external dependencies is inaccurate when it depends on CoinGecko, DefiLlama/manual external data, internet connectivity, and optionally OpenClaw cron. In security-sensitive or offline deployments, this can cause policy bypass, failed execution, or unintended data flows because reviewers may not apply the scrutiny normally given to network-dependent skills.

Description-Behavior Mismatch

High

• Confidence: 99% confidence
• Finding: The script presents itself as producing daily market analysis and macro news, but the OHLC candles and news are hard-coded rather than sourced dynamically. In a financial-analysis skill, fabricated data is dangerous because users may make trading or risk decisions based on false information while believing it is current and factual.

Intent-Code Divergence

High

• Confidence: 98% confidence
• Finding: The comments claim CoinGecko/API/news sourcing, but the implementation returns static mock data. This mismatch is security-relevant because it misleads reviewers and users about the trustworthiness and freshness of the analysis, creating a deceptive output channel in a finance-oriented skill.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The report explicitly encourages users to bridge assets, interact with testnets, and join Discord/Twitter quests without any warning about wallet-drain risks, phishing, malicious smart contracts, fake social accounts, transaction costs, or use of burner wallets. In a crypto-airdrop skill, this context makes the omission more dangerous because users are being nudged toward real blockchain interactions where scams and wallet compromise are common.

VirusTotal

60/60 vendors flagged this skill as clean.