Scan Report
10 /100
reviewstudio
Review Studio integration for managing data, records, and workflow automation via Membrane CLI
Review Studio integration skill using the legitimate Membrane CLI; all capabilities are properly declared and no hidden functionality was detected.
Safe to install
Skill is safe for use. Monitor for any changes to the Membrane CLI package or domain that could introduce supply-chain risks.
Findings 2 items
| Severity | Finding | Location |
|---|---|---|
| Low | Global npm package installation | SKILL.md:39 |
| Low | External URLs to third-party domains | SKILL.md:7 |
| Resource | Declared | Inferred | Status | Evidence |
|---|---|---|---|---|
| Shell | WRITE | WRITE | ✓ Aligned | SKILL.md:39 npm install -g @membranehq/cli; SKILL.md:44 membrane login; SKILL.md… |
| Network | READ | READ | ✓ Aligned | SKILL.md:52 membrane action list; SKILL.md:59 membrane action run; SKILL.md:74 m… |
| Filesystem | NONE | NONE | — | No filesystem operations declared or observed |
| Environment | NONE | NONE | — | No direct environment variable access; credentials managed by Membrane server-si… |
| Skill Invoke | NONE | NONE | — | No cross-skill invocation declared |
| Clipboard | NONE | NONE | — | No clipboard access |
| Browser | NONE | NONE | — | Browser used only for OAuth flow (declared), no persistent browser control |
| Database | NONE | NONE | — | No database access |
2 findings
Medium External URL 外部 URL
https://getmembrane.com SKILL.md:7 Medium External URL 外部 URL
https://support.reviewstudio.com/en/ SKILL.md:19 File Tree
1 files · 4.4 KB · 124 lines Markdown 1f · 124L
└─
SKILL.md
Markdown
Dependencies 1 items
| Package | Version | Source | Known Vulns | Notes |
|---|---|---|---|---|
@membranehq/cli | latest | npm | No | Version not pinned; global install recommended by SKILL.md |
Security Positives
✓ All shell operations (npm install, membrane CLI) are explicitly declared in SKILL.md
✓ No credential harvesting — credentials are managed server-side by Membrane
✓ No base64, eval, or obfuscated code patterns detected
✓ No hidden HTML comments or steganographic payloads
✓ No access to sensitive local paths (~/.ssh, ~/.aws, .env)
✓ No subprocess or code execution beyond declared CLI tooling
✓ No data exfiltration or suspicious network behavior
✓ Skill is a pure documentation file with no executable code
✓ Best practices are well documented (preferring Membrane actions over raw API calls)