Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
hyperliquid-btc-auto-trader
v1.0.0Autonomous BTC-USDC trading bot on Hyperliquid mainnet using multi-timeframe anchored VWAP and strict safety limits for live market execution.
⭐ 0· 72·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The code implements an on‑chain trading bot using the Hyperliquid SDK and therefore legitimately needs a wallet address and private key. However the registry metadata declares no required environment variables or primary credential while config.py and SKILL.md explicitly refer to HYPERLIQUID_WALLET_ADDRESS and HYPERLIQUID_PRIVATE_KEY. That metadata mismatch is an incoherence that affects trust and installation decisions.
Instruction Scope
SKILL.md instructs you to export a private key and to start the bot as an autonomous live trader; it also contains duplicated/corrupted content (a second injected markdown section and an unfinished '#### 2. of `SKILL.md`' fragment). The SKILL.md claims 'All 8 hard safety limits are coded and cannot be bypassed', but the code does not implement several of those safeguards (daily_loss and consecutive_losses are tracked but never updated; CircuitBreaker exists but is not wired into the run loop). This is scope creep/misrepresentation: instructions promise stronger safety than the code provides.
Install Mechanism
There is no explicit install spec in the registry, but a requirements.txt lists dependencies (hyperliquid-python-sdk, pandas, pandas_ta, python-dotenv, schedule, numpy). That implies the agent/user must install PyPI packages before running; this is expected but should be made explicit. No external download URLs or opaque installers are present in the manifest (lower install risk), but dependencies from PyPI still deserve review.
Credentials
Requiring a wallet private key and address is proportionate to a trading bot, but the skill metadata does NOT declare those required env vars while the SKILL.md and config.py do. The skill requests a highly sensitive secret (HYPERLIQUID_PRIVATE_KEY) — the registry should declare that as the primary credential. Also consider that the SKILL.md asks you to run on mainnet and sign live trades: supplying a private key to untrusted code risks fund loss; the code does not show any key-protection or usage limits beyond calling the Exchange with the key.
Persistence & Privilege
always:false and default autonomous invocation are set (normal). The skill does not request permanent platform privileges or modify other skills' configs. There is no indication it persists beyond its own runtime files. However, autonomous trading with a private key remains high-impact — combine with other concerns before enabling.
What to consider before installing
This skill will attempt to run live market trades and requires your wallet/private key — do not provide a mainnet private key unless you fully audit and trust the code. Specific actions to take before installing or running: 1) Treat the registry metadata mismatch as a red flag: confirm with the author why required env vars were omitted. 2) Audit the code paths that use PRIVATE_KEY and Exchange.market_open; verify order sizing, leverage enforcement, and stop-loss logic. 3) Note that several safety claims in SKILL.md are inaccurate: daily_loss and consecutive-loss enforcement and the circuit-breaker are not implemented/wired in; fix or confirm before running. 4) Prefer testing on a sandbox/testnet account with a small balance or a noncustodial key with no funds. 5) If you do run on mainnet, rotate keys afterward and consider hardware/signing proxies so the skill never sees the raw private key. 6) Ask for corrected metadata (declare primary env var) and a cleaned SKILL.md before trusting autonomous operation.Like a lobster shell, security has layers — review code before you run it.
latestvk97a5pqjq5w5vfnwb392gjg2dd83swsn
License
MIT-0
Free to use, modify, and redistribute. No attribution required.