Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Apploi
v1.0.0Apploi integration. Manage data, records, and automate workflows. Use when the user wants to interact with Apploi data.
⭐ 0· 16·0 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 claims to integrate with Apploi and its SKILL.md consistently shows how to do that via the Membrane CLI. However, the registry metadata declares no required binaries or credentials while the instructions explicitly require installing and using the `membrane` CLI and a Membrane account — a mismatch between declared requirements and runtime needs.
Instruction Scope
The SKILL.md contains straightforward, scoped instructions for installing the Membrane CLI, logging in, creating a connection, listing actions, running actions, and proxying requests to Apploi. It does not instruct the agent to read unrelated local files or environment variables, nor to exfiltrate data to unexpected endpoints. It does, however, instruct you to route API requests through Membrane (see privacy note below).
Install Mechanism
There is no formal install spec in the registry (instruction-only), but the README directs users to install @membranehq/cli from npm (public registry). Installing an npm CLI is typical here, but the skill should have declared the required binary in metadata. Installing global npm packages has the usual supply-chain risk; verify the package's publisher and source.
Credentials
The skill requests no local secrets and explicitly recommends letting Membrane handle auth (no API keys stored locally). That is proportionate to the stated purpose, but it also means sensitive Apploi data will transit through Membrane's service and be accessible to that third party. If you will handle personal or protected health information (PHI), confirm Membrane's data handling, retention, and compliance posture before proceeding.
Persistence & Privilege
The skill does not request always:true or other elevated persistence. It is user-invocable and allows autonomous invocation (normal default). There is no indication it will modify other skills or agent configuration beyond using the Membrane CLI as instructed.
Scan Findings in Context
[NO_SCAN_RESULTS] expected: This is an instruction-only skill with no code files; the static scanner had nothing to analyze. The security surface is the SKILL.md instructions and the npm package the user is asked to install.
What to consider before installing
Before installing: 1) Note the SKILL.md requires the Membrane CLI (npm package @membranehq/cli) and a Membrane account even though the registry metadata doesn't declare the binary/credentials — verify you are comfortable installing a global npm CLI and update any org policy accordingly. 2) Understand that API calls and any data (including candidate or healthcare data) will be proxied through Membrane — if you handle PII/PHI, confirm Membrane's security/compliance (encryption, retention, HIPAA if needed) and privacy policy. 3) Verify the npm package and GitHub repository authorship and integrity (package owner on npm, package version, checksums) before installation to reduce supply-chain risk. 4) Prefer using npx (one-off) or reviewing the package source before a global install, and avoid pasting authentication codes into untrusted environments. If you want, I can summarize exact checks to run on the npm package and the Membrane privacy/compliance pages.Like a lobster shell, security has layers — review code before you run it.
latestvk973q2kdwn7y3x0rrgav392g2x846rwk
License
MIT-0
Free to use, modify, and redistribute. No attribution required.