crypto-wallet

ISSUES FOUND max severity CRITICALSkillSpector Safe 20 registry clawhub.ai last scanned 2026-02-05 1 scan

3 findings (1 critical, 2 high), mainly data exfiltration, unauthorized tool use, social engineering. Most recent scan 2026-02-05.

This skill presents CRITICAL security risks and should NOT be used in its current form. The fundamental issue is that it claims to provide cryptocurrency wallet management capabilities (checking balances, sending tokens, viewing transactions across 6 blockchains) but contains ZERO implementation code. This creates a dangerous situation where: (1) Users might trust the skill with sensitive financial operations based on its professional presentation, (2) The agent would need to generate wallet management code on-the-fly without security review, (3) No secure key management, transaction signing, or validation logic exists, (4) The skill cannot deliver on its stated capabilities. Beyond the missing implementation, the use case itself (AI agent managing cryptocurrency wallets) is fundamentally inappropriate for agent skills due to the extreme security sensitivity of private key handling and irreversible financial transactions. RECOMMENDATION: Remove this skill entirely. If cryptocurrency integration is needed, it should be through secure, audited external services with hardware wallet integration, not agent-generated code.
Scanner's overall assessment (LLM analyzer)

Findings3

Critical1

High2

Medium0

Low0

Analyzersstatic behavioral llm trigger meta

Second scanner: NVIDIA SkillSpector

VerdictSafe 20

Score20 / 100

Issues1

CategoriesYARA Match

Version2.12.0 (static)

The two scanners disagree: Cisco rates this CRITICAL and SkillSpector found nothing. Check the false-positive register; signature matches on documentation are the usual cause. How the two scanners compare across the whole corpus: Two scanners, one corpus.

What this skill does

Multi-chain cryptocurrency wallet management. Check balances, send tokens, view transaction history across Ethereum, Solana, Bitcoin and more.

Package: 1 file, 853 B
SKILL.md: 91 words, 5 sections
Code: None. Instructions only.
Requires: bins: curl jq

SKILL.md covers: Crypto Wallet 💰 · Supported Chains · Features · Usage Examples · Safety Rules

Findings

CRITICAL Missing Implementation Creates Critical Security Gap Data Exfiltrationllm

The skill claims to manage cryptocurrency wallets and send tokens across multiple blockchains, but contains NO implementation code whatsoever. This creates a critical security risk because: (1) The agent would need to improvise implementation, potentially creating insecure wallet handling code on-the-fly, (2) There is no secure key management implementation, (3) Transaction signing logic is absent, (4) No validation or safety checks exist in code. The skill promises 'Send tokens (with confirmation)' but provides no mechanism to safely handle private keys, sign transactions, or validate addresses. This is effectively a prompt that could lead the agent to generate dangerous cryptocurrency handling code without proper security controls.

Features list includes 'Send tokens (with confirmation)' and 'Check wallet balances' but no Python/Bash scripts exist to implement these security-critical operations. The skill would require the agent to generate wallet management code dynamically.

Remediation: Either: (1) Remove this skill entirely - cryptocurrency wallet management should not be handled by AI agents due to extreme security sensitivity, OR (2) Provide complete, audited implementation with: secure key storage (hardware wallet integration), transaction signing with multi-factor confirmation, address validation, rate limiting, and comprehensive error handling. Recommend option 1 - this use case is inappropriate for agent skills.

HIGH Phantom Tool Declaration - No Implementation for Claimed Capabilities Unauthorized Tool Usellm

The skill declares it can perform security-critical operations (check balances, send tokens, view transaction history) across multiple blockchains but provides zero implementation. This is tool poisoning through omission - the skill's metadata claims capabilities that don't exist in code form. The agent would be forced to either: (1) Fail to execute the skill's stated purpose, or (2) Generate implementation code on-the-fly without security review. The 'requires: bins: [curl, jq]' suggests network operations but no scripts use these tools.

SKILL.md:1

YAML declares 'requires: bins: [curl, jq]' implying network API calls, but no scripts exist. Instructions promise 'Send 0.1 ETH to 0x...' functionality with no implementation.

Remediation: Provide complete implementation scripts that match declared capabilities, or remove capability claims from the description. For cryptocurrency operations, implementation must include: API endpoint validation, rate limiting, transaction simulation/dry-run, and explicit user confirmation workflows.

HIGH Deceptive Capability Claims - Cryptocurrency Operations Without Code Social Engineeringllm

The skill description and instructions create false expectations of a functional cryptocurrency wallet manager. Users would reasonably expect this skill to safely handle their crypto assets based on the detailed feature list (balance checking, sending tokens, transaction history, portfolio overview across 6 blockchains). However, the complete absence of implementation code means the skill cannot deliver on these promises. This is social engineering through misleading metadata - users might trust the skill with sensitive wallet operations based on its professional presentation, unaware that no vetted security code exists.

SKILL.md

Description: 'Multi-chain cryptocurrency wallet management. Check balances, send tokens, view transaction history' but zero implementation files. Features section lists 6 specific capabilities with no code to execute them.

Remediation: Update description to accurately reflect that this is a template/placeholder, not a functional wallet manager. Add prominent warnings that cryptocurrency operations require security-audited implementation. Consider removing this skill entirely as the use case (AI agent managing crypto wallets) presents unacceptable security risks.

What is in the package

File	Kind	Size
`SKILL.md`	doc	853 B

Package contents recorded 2026-10-22. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.

What we checked

Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
Llm analyzer. A language model reads the skill and reports intent-level issues the rules cannot express.
Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.
Meta analyzer. A second model pass that validates, deduplicates and re-scores the other analyzers' findings.

What we did not check

Runtime behaviour. The skill was not executed; findings come from reading its files.
Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
Content the analyzers cannot read: images, binaries, and some non-English text.
Known scanner bypass classes. See the methodology and limitations page.

Sources

Repository: https://clawhub.ai/skills/crypto-wallet
Raw scan result: crypto-wallet-scan.json
Badge for your README: ![skillscan.io](https://skillscan.io/badge/clawhub-ai-crypto-wallet.svg)
Request a re-scan