Security audit
Security checks for vulnerabilities and agentic risk
This is a disclosed paper-trading skill that fetches public crypto prices and updates a local mock portfolio, with no evidence of real trading, credential use, exfiltration, or hidden behavior.
Install only if you are comfortable with a mock trading script contacting CoinGecko for price data and modifying a local portfolio JSON file. Do not enable HEARTBEAT.md or cron automation unless you intentionally want it to run repeatedly, and remember that this is paper trading only, not financial advice or real exchange trading.
The skill description promises paper trading behavior but omits that it fetches live external market data and overstates implemented strategy support. This mismatch can mislead users and reviewers about both the skill's network behavior and its functional limits, causing unapproved data egress and incorrect trust in how the bot operates.
The skill instructs the agent to run code that reads and writes local files and performs network access, but it declares no explicit tool scope or permissions. That omission weakens reviewability and consent boundaries, making it easier for an agent to perform side effects the user or platform did not clearly authorize.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
import os
def get_crypto_price(asset_id="bitcoin"):
url = f"https://api.coingecko.com/api/v3/simple/price?ids={asset_id}&vs_currencies=usd"
response = requests.get(url)
data = response.json()
return data[asset_id]["usd"]
The code writes the portfolio JSON back to disk, replacing the existing file contents, but there is no comment, docstring, or user-facing warning near the write operation explaining that the file will be modified. Although trade actions are printed, the persistence step itself is silent and can alter user data on every run.
The skill tells the agent to copy a template portfolio and later update that local file, but it does not warn the user that local files will be created and modified. Even though this is a mock trading context, silent file writes and especially persistence via HEARTBEAT.md or cron can create unintended state changes and surprise automation on the user's system.