Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Campay

v1.0.0

CamPay integration. Manage data, records, and automate workflows. Use when the user wants to interact with CamPay data.

0· 21·0 current·0 all-time
byMembrane Dev@membranedev
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
CryptoCan make purchases
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
The SKILL.md describes a CamPay integration implemented via the Membrane CLI, which is coherent with the skill's name and description. However the skill metadata declared no required binaries while the runtime docs instruct installing and running the @membranehq/cli (global npm or npx). Also the 'Official docs' link points to Apple Pay (developer.apple.com/apple-pay), which is likely a copy/paste error and reduces confidence in the package provenance.
Instruction Scope
Instructions confine themselves to using the Membrane CLI and Membrane's proxy for CamPay API calls; they do not instruct reading arbitrary local files or exporting secrets. The skill requires a Membrane account and browser-based auth flows. The instructions do tell users to install/run npm-installed tooling and to pass JSON to CLI commands — normal for this type of integration.
!
Install Mechanism
There is no declared install spec, yet the SKILL.md tells users to run 'npm install -g @membranehq/cli' or use npx. Global npm installs can execute arbitrary code on the machine and the skill did not declare this dependency in its metadata. While the installation source (@membranehq on npm and GitHub repo are mentioned), the skill should explicitly declare required binaries/install steps and avoid recommending global installs without justification.
Credentials
The skill does not request environment variables or local credentials and explicitly advises letting Membrane manage credentials server-side. It does require a network connection and a Membrane account for browser-based authentication, which is proportionate to the stated purpose.
Persistence & Privilege
The skill does not request always:true, does not declare persistent system-wide changes, and contains no instructions to modify other skills or system-wide agent configuration. Autonomous invocation is allowed by platform default but not specifically elevated by this skill.
What to consider before installing
This skill appears to be a wrapper around the Membrane CLI for accessing CamPay, but take these precautions before installing or running it: - Verify the upstream project: inspect the @membranehq/cli package on npm and the referenced GitHub repository (https://github.com/membranedev/application-skills) to confirm maintainers and release authenticity. - Prefer running with npx (one-off) rather than a global npm install, or at least pin the package version, because global npm installs run code on your machine. - The SKILL.md metadata has small inconsistencies (it omits the 'membrane' binary requirement and links to Apple Pay docs), which suggests copy/paste or sloppy editing — ask the publisher to clarify these points. - Confirm you trust Membrane as the service that will hold/refresh credentials; read its privacy/security docs and terms before connecting production payment accounts. - When possible, run initial commands manually in a controlled environment (not granting the agent full autonomous execution) so you can observe any browser auth flows or unexpected network activity. If you can verify the package source and accept the risk of installing the CLI, the skill's behavior is coherent; if you cannot verify provenance, avoid installing or running the global npm command.

Like a lobster shell, security has layers — review code before you run it.

latestvk975grm4243104vmnf1zba04jx8483mb

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments