ClawHub
Back to skill

Security audit

Spot

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent Binance Spot API helper, but it tells agents to persist high-value trading credentials in plaintext and enables live account-changing operations.

Review before installing. Use this only with testnet or tightly scoped Binance API keys, never with withdrawal permission, and do not let an agent store live API keys or secrets in TOOLS.md or any repository/chat-visible file. Prefer a secure secret store, IP allowlisting, least-privilege keys, and explicit confirmation for every live order, cancellation, amendment, or other account-changing operation.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:278
Finding

Plaintext Storage of Binance API Credentials in TOOLS.md

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
references/authentication.md:78
Finding

Binance Secret Key Exposed Through Command-Line Process Arguments

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill explicitly tells the agent to store Binance API keys and secrets in TOOLS.md without any protection model, encryption, or warning. Plaintext persistence of exchange credentials is highly dangerous because anyone with file, repo, log, or prompt access could recover the secrets and place trades, cancel orders, or access account data.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill goes beyond making Spot API requests and instructs the agent to collect, store, and manage Binance API credentials in local markdown files. Persisting exchange credentials creates a new secret-management surface that is unnecessary for the stated function and materially increases the risk of credential disclosure, misuse, or later exfiltration by other tools or prompts.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The file says secrets should never be displayed in full, yet it also instructs users to provide raw key material in a two-line file format and shows embedded credential fields elsewhere. That contradiction normalizes plaintext secret handling and can lead operators or downstream agents to ingest, persist, or expose live API credentials despite the masking guidance.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill exposes state-changing capabilities such as order placement and cancellation, but only mandates explicit confirmation for mainnet transactions and does not comprehensively gate other destructive authenticated actions. In this context, even seemingly routine authenticated endpoints can have financial or operational consequences, so weak confirmation rules increase the chance of accidental or manipulated trading actions.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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/authentication.md (reported line 70)May include surrounding context.

Request:

bash
curl -X POST "https://api.binance.com/api/v3/order" \
  -H "X-MBX-APIKEY: your_api_key" \
  -H "User-Agent: binance-spot/1.0.1 (Skill)" \
  -d "symbol=BTCUSDT&side=BUY&type=MARKET&quantity=0.001&timestamp=1234567890123&signature=..."

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/authentication.md (reported line 70)May include surrounding context.

Request:

bash
curl -X POST "https://api.binance.com/api/v3/order" \
  -H "X-MBX-APIKEY: your_api_key" \
  -H "User-Agent: binance-spot/1.0.1 (Skill)" \
  -d "symbol=BTCUSDT&side=BUY&type=MARKET&quantity=0.001&timestamp=1234567890123&signature=..."

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

A Spot-only skill should not define or normalize handling of unrelated account material such as futures-keys. Expanding the scope of accepted credentials increases the blast radius if secrets are mishandled and makes it easier to expose or misuse higher-risk exchange accounts not needed for the declared purpose.

Content

No source excerpt is available for this finding.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:295