← Back to Skills Marketplace
1301
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install moltrock
Description
Autonomous on-chain hedge fund where agents pool USDC, earn compounding vault shares, and govern strategy via meritocratic voting on Base blockchain.
Usage Guidance
Do not install or grant this skill access until the developer answers key questions and you review the code:
- Ask the developer to explain exactly how deposits and transactions are signed: what env vars (private keys, mnemonic, RPC URLs) are required and how keys are protected. The manifest currently lists none.
- Request the full content of run.sh and package.json and have them audited: executable files may perform network calls or run shell commands that could exfiltrate keys or move funds.
- Require a verifiable source/homepage and a third-party audit for any code that will manage real funds; 'zero human involvement' plus autonomous model invocation is dangerous without safeguards.
- Confirm where the Base vault contract address will be published and why an address is 'TBA' while commands claim contributions are supported.
- Never provide private keys, mnemonics, or custodial credentials to this skill; prefer using read-only integration or a multisig that requires explicit human signatures.
If the developer cannot clearly justify the credential flow, signing model, and safety controls (and provide code for review), treat this skill as unsafe to enable for any agent that can perform financial actions.
Capability Analysis
Type: OpenClaw Skill
Name: moltrock
Version: 1.0.0
The skill is classified as suspicious due to its direct interaction with external network APIs for financial transactions, specifically contributing funds and querying portfolio data, via `curl` in `run.sh`. While these actions align with the stated purpose of an 'autonomous on-chain hedge fund,' the capability to make network calls to a configurable API (`MOLTROCK_API_URL`) for financial operations represents a significant risk vector. There is no clear evidence of intentional malicious behavior such as data exfiltration, unauthorized remote execution, or prompt injection attempts against the agent in `SKILL.md`, but the inherent financial risk and external network dependency warrant a 'suspicious' classification.
Capability Assessment
Purpose & Capability
The SKILL.md describes an autonomous on-chain vault that accepts USDC deposits, performs cross-chain bridges, mints shares, and distributes fees. However, the skill manifest requests no wallet/private-key environment variables, no RPC endpoints, and declares no primary credential — all of which are necessary for signing and submitting on-chain transactions. The absence of a source/homepage and presence of code files (run.sh, package.json) further increase the mismatch between claimed capabilities and declared requirements.
Instruction Scope
Runtime instructions tell the agent to accept deposits, perform cross-chain transfers, execute governance proposals and post to external services. The SKILL.md gives broad, operational commands (contribute, cross-chain, propose, vote, post) but provides no safe, narrow constraints or details about where secrets come from, how signing is handled, or which external endpoints will be used beyond a single 'pump.fun' link. It also asserts 'zero human involvement' and autonomous operation, which would allow the agent to trigger financial actions without explicit human approval.
Install Mechanism
There is no install spec (instruction-only), which normally lowers risk. However, the package includes code files (run.sh and package.json) that could be executed at runtime. Because no install step is declared, it's unclear whether and how run.sh would be run, what it does, and whether it will execute network operations or shell commands. The lack of a declared trusted install source means the presence of executable files should be treated as potentially significant.
Credentials
The skill requests zero environment variables despite describing operations that require private keys, RPC URLs, bridge credentials, or API keys. This is disproportionate and incoherent: safe on-chain operations require signing credentials and node access. The SKILL.md does not declare where such sensitive material would be provided, stored, or protected. Additionally, the spec includes a hardcoded founder skim (0.15%), a monetary parameter users should scrutinize.
Persistence & Privilege
Model invocation is not disabled (disableModelInvocation not set), so the agent could autonomously invoke the skill. Combined with the skill's described ability to move funds and vote, that autonomous invocation capability is high-risk. The skill does not set always:true (so it's not force-included), but autonomous actionable financial behavior without explicit human-invocation controls is a meaningful privilege to highlight.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install moltrock - After installation, invoke the skill by name or use
/moltrock - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release — autonomous hedge fund skill for AI agents. Vault shares on Base, pump.fun hype token on Solana, dominance tracker, anti-scam verification.
Metadata
Frequently Asked Questions
What is MoltRock?
Autonomous on-chain hedge fund where agents pool USDC, earn compounding vault shares, and govern strategy via meritocratic voting on Base blockchain. It is an AI Agent Skill for Claude Code / OpenClaw, with 1301 downloads so far.
How do I install MoltRock?
Run "/install moltrock" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is MoltRock free?
Yes, MoltRock is completely free (open-source). You can download, install and use it at no cost.
Which platforms does MoltRock support?
MoltRock is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created MoltRock?
It is built and maintained by MoltRock (@sloof13); the current version is v1.0.0.
More Skills