ClawHub
Back to skill

Security audit

BTC Risk Radar

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed, read-only Bitcoin market risk snapshot tool that queries public exchange APIs and prints analysis without using accounts, wallets, or persistent access.

Install only if you are comfortable with the skill making unauthenticated outbound requests to public crypto exchange APIs for market data. It does not appear to access wallets, exchange accounts, credentials, or local private files, and its trading outputs should be treated as heuristic analysis rather than financial advice.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill documentation instructs users to run a Python script that performs public HTTP requests, but the skill manifest does not declare any explicit tool scope such as allowed network access. This creates a permission-boundary mismatch: reviewers and execution environments cannot easily verify or constrain the skill’s actual capabilities, which increases the risk of unintended outbound access or future scope creep being introduced without notice.

External Transmission

Medium
Category
Data Exfiltration
Content
SKILL_VERSION = "0.1.1"
DERIBIT = "https://www.deribit.com/api/v2/public"
BINANCE = "https://api.binance.com/api/v3"
OKX = "https://www.okx.com/api/v5"
BYBIT = "https://api.bybit.com/v5"
PUBLIC_SOURCES = [
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
DERIBIT = "https://www.deribit.com/api/v2/public"
BINANCE = "https://api.binance.com/api/v3"
OKX = "https://www.okx.com/api/v5"
BYBIT = "https://api.bybit.com/v5"
PUBLIC_SOURCES = [
    "Deribit Public API: /public/get_instruments, /public/get_order_book, /public/get_book_summary_by_currency, /public/get_index_price, /public/get_book_summary_by_instrument",
    "Coinbase Public API: /v2/prices/BTC-USD/spot",
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
data["data_gaps"].append("binance_spot_unavailable")

    try:
        cb = get("https://api.coinbase.com/v2/prices/BTC-USD/spot")
        data["spot"]["coinbase"] = float(cb["data"]["amount"])
    except Exception:
        data["data_gaps"].append("coinbase_spot_unavailable")
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

No suspicious patterns detected.