On-Chain Skill Audit

On-chain skill provenance registry. Check, register, audit, and vouch for agent skills on Solana. Use when evaluating skill safety, registering new skills, or looking up provenance before installation.

Before installing or running this skill, consider the following: (1) it will read local skill.md files you point it at and can publish full reports on-chain — do not register or inscribe content you don’t want public; (2) the SKILL.md expects npm packages and a Solana signer/IQ token but the skill metadata does not declare them — confirm how the agent will obtain signing capability (never supply private keys unless you understand and trust the process); (3) ask the publisher for an explicit install guide and a privacy statement about what gets inscribed to chain and where ZeroLeaks/codeIn upload data; (4) verify the referenced program ID and npm package names independently (typosquatting is possible); (5) if you only want to read registry data, prefer read-only operations and avoid giving signer access or running inscription steps.

Type: OpenClaw Skill Name: onchain-skill-audit Version: 0.1.1 The skill is classified as suspicious due to its inherent risky capabilities, even though they are plausibly needed for its stated purpose. The `/register-skill` command in `skill.md` instructs the agent to "Read skill.md at given path", which grants file system access based on user input. While intended for hashing skill content, this capability could be abused by a malicious user to read arbitrary local files. Additionally, the `registerSkill` and `auditSkill` functions, as described in `skill.md`, accept a `codeInTx` parameter, allowing arbitrary data to be inscribed on-chain, which presents a potential data exfiltration vector if sensitive information were passed to it. The skill also relies on an external npm package (`@rocketlabs/skill-audit`), introducing a supply chain risk.