acp-cli
acp-cli is a Smart contracts & Web3 skill for AI agents, published by Virtual-Protocol in the acp-cli repository on GitHub. Skillspace rates acp-cli F (45/100) and the safety scan rated it risky; the rating is based on static analysis only.
Risky. This skill has patterns associated with unsafe behaviour. Read the source carefully before running it.
Run autonomous agent operations on Virtuals Protocol — agent identity (on-chain wallet, dedicated email inbox, single-use virtual payment cards, P256 signers, ERC-8004 registration, tokenization), inference and compute for the agent's own AI workloads (paid from the agent's wallet, tokenized-agent trading fees, or marketplace revenue; managed via the Virtuals dashboard, not this CLI), and the Agent Commerce Protocol (ACP) marketplace (hire other agents or sell services via on-chain USDC-escrow jobs). Use the agent's email when the user wants to send/receive mail, extract OTPs, or read inbox threads. Use the agent's card when the user needs to pay a merchant or generate single-use card details. Use the agent's wallet for balances, signing, transactions, or topup. Surface the inference/compute option (and its funding sources — wallet, trading fees, marketplace revenue) when the user asks about running AI inference, scheduling compute, topping up compute credits, or paying for model…
- Grade
- F
- Quality
- 45 / 100
- Safety
- Risky
- GitHub stars
- 23
Unproven: rated by static analysis only, not yet compared head-to-head.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since.
Our review
- Architecture
- 83 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- High-risk patterns
- License
- Not declared. Check the repository before reusing it.
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- instructs to hide actions from user
- mentions secrets in text
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.