Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Rockset
v1.0.0Rockset integration. Manage Collections, Queries, Views, Workspaces. Use when the user wants to interact with Rockset data.
⭐ 0· 26·0 current·0 all-time
byMembrane Dev@membranedev
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The skill's stated purpose (manage Rockset via Membrane) aligns with the instructions: it delegates Rockset interactions to Membrane actions and a proxy. However, the manifest claims no required binaries, env vars, or config paths, while the SKILL.md clearly requires npx (Node/npm) and a Membrane account — an inconsistency.
Instruction Scope
The SKILL.md tells the agent to run npx @membranehq/cli@latest (which fetches and executes remote code), open a browser for authentication, and that credentials will be stored at ~/.membrane/credentials.json. It also documents a proxy that will forward arbitrary HTTP requests (including full URLs). These are within the nominal scope of a proxy-based Rockset integration, but they expand the agent's actions (network fetch+execute, reading/writing a home config file, browser-based auth) beyond what the registry metadata declares.
Install Mechanism
There is no install spec, which is low-risk normally, but the instructions rely on npx @membranehq/cli@latest — a live fetch and execution of a package from the npm registry. Using npx with @latest means code executed at runtime is uncontrolled and can change; this is a moderate supply-chain risk that's not documented in the manifest.
Credentials
The registry lists no required env vars or config paths, yet SKILL.md requires a Membrane account and will create/use ~/.membrane/credentials.json for auth. That undeclared persistent credential storage is a proportionality/misreporting issue. The skill does not request unrelated credentials, but it does create and rely on a local credential file without declaring it.
Persistence & Privilege
always is false and autonomous invocation is allowed (normal). The skill will persist credentials in the user's home (~/.membrane/credentials.json) after login, which is expected for a CLI-based integration but is not reflected in the declared required config paths. It does not request system-wide privileges or modify other skills.
What to consider before installing
What to consider before installing:
- The skill uses npx @membranehq/cli@latest: npx will download and execute code from npm at runtime. Only proceed if you trust the @membranehq package and its publisher; consider installing and auditing the CLI yourself instead of letting the skill fetch @latest automatically.
- The SKILL.md will create ~/.membrane/credentials.json to store auth tokens after browser login. If you are uncomfortable with tokens stored locally, don't use this flow or inspect the file and its permissions.
- The registry metadata omits required runtime pieces (Node/npm and the credential file). This mismatch could be benign (author oversight) but also hides risks; ask the publisher for a homepage, package repository, and verification of the Membrane CLI package.
- The proxy can forward arbitrary HTTP requests — verify the agent will only send requests you expect (to Rockset) and not arbitrary external endpoints.
If you decide to proceed: pin the CLI to a known-good version (avoid @latest), install the CLI yourself from a trusted source, and verify or sandbox the credential file and network access. If you need higher assurance, request the skill author add explicit manifest entries for required binaries and config paths and provide a homepage/repository for review.Like a lobster shell, security has layers — review code before you run it.
latestvk97eta9j3y9ck7fekgn8p2gn4h848qd1
License
MIT-0
Free to use, modify, and redistribute. No attribution required.