ClawHub
Back to skill

Security audit

Binance P2p

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for Binance P2P lookups, but it handles financial API credentials and includes a shell example that can expose keys if copied with real credentials.

Review this skill before installing if you plan to use personal order history. Use a Binance API key with read-only permission only, enable IP allowlisting where possible, avoid putting real keys into the Bash example or committed .env files, and prefer a secure runtime secret mechanism or in-process client that does not expose secrets in command arguments.

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 (1)

T09 · Insecure Skill Coding Practices

Warning
Location
references/authentication.md:71
Finding

Binance API Credentials Exposed Through Script Storage and Process Arguments

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/authentication.md (reported line 101)May include surrounding context.

md
* Never share your secret key
* Use IP whitelist in Binance API settings
* Enable only required permissions (Enable Reading for P2P order history)
* Store credentials securely in .env file (add to .gitignore)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill hardcodes an English locale in generated Binance ad links (/en/adv?...) without checking the user's preferred language or region. This can misroute users to an unexpected localized experience, create confusion, and in some cases weaken trust signals if the displayed page language differs from the user's normal Binance interface.

Content

No source excerpt is available for this finding.

Excessive Permissions

Low
Category
Privilege Escalation
Confidence
80% confidence
Finding

Skill requests more permissions than appear necessary for its stated functionality. Review if elevated access is justified.

Content

Scanner excerpt · SKILL.md (reported line 63)May include surrounding context.

md
- Secret Key: always mask; show **only last 5**: `***...c123`

### Permission minimization
- Binance API permissions: **Enable Reading** only.
- Do NOT request/encourage trading, withdrawal, or modification permissions.

### Storage guidance