cloudmersive — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited cloudmersive (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Cloudmersive is a cybersecurity vendor offering APIs for malware scanning, virus detection, and content safety. Developers and organizations use these APIs to integrate security features into their applications and workflows. This helps them protect against threats and ensure compliance.
Official docs: https://api.cloudmersive.com/docs/
This skill uses the Membrane CLI to interact with Cloudmersive. Membrane handles authentication and credentials refresh automatically — so you can focus on the integration logic rather than auth plumbing.
Install the Membrane CLI so you can run membrane from the terminal:
npm install -g @membranehq/cli@latestmembrane login --tenant --clientName=<agentType>This will either open a browser for authentication or print an authorization URL to the console, depending on whether interactive mode is available.
Headless environments: The command will print an authorization URL. Ask the user to open it in a browser. When they see a code after completing login, finish with:
membrane login complete <code>Add --json to any command for machine-readable JSON output.
Agent Types : claude, openclaw, codex, warp, windsurf, etc. Those will be used to adjust tooling to be used best with your harness
Use membrane connection ensure to find or create a connection by app URL or domain:
membrane connection ensure "https://cloudmersive.com" --jsonThe user completes authentication in the browser. The output contains the new connection id.
This is the fastest way to get a connection. The URL is normalized to a domain and matched against known apps. If no app is found, one is created and a connector is built automatically.
If the returned connection has state: "READY", skip to Step 2.
#### 1b. Wait for the connection to be ready
If the connection is in BUILDING state, poll until it's ready:
npx @membranehq/cli connection get <id> --wait --jsonThe --wait flag long-polls (up to --timeout seconds, default 30) until the state changes. Keep polling until state is no longer BUILDING.
The resulting state tells you what to do next:
clientAction object describes the required action:clientAction.type — the kind of action needed:"connect" — user needs to authenticate (OAuth, API key, etc.). This covers initial authentication and re-authentication for disconnected connections."provide-input" — more information is needed (e.g. which app to connect to).clientAction.description — human-readable explanation of what's needed.clientAction.uiUrl (optional) — URL to a pre-built UI where the user can complete the action. Show this to the user when present.clientAction.agentInstructions (optional) — instructions for the AI agent on how to proceed programmatically.After the user completes the action (e.g. authenticates in the browser), poll again with membrane connection get <id> --json to check if the state moved to READY.
error field for details.Search using a natural language description of what you want to do:
membrane action list --connectionId=CONNECTION_ID --intent "QUERY" --limit 10 --jsonYou should always search for actions in the context of a specific connection.
Each result includes id, name, description, inputSchema (what parameters the action accepts), and outputSchema (what it returns).
| Name | Key | Description |
|---|---|---|
| Recognize Receipt from Photo | recognize-receipt-from-photo | Extracts structured data from a photo of a receipt including business name, address, items, subtotal, and total. |
| Extract Text from Image (OCR) | extract-text-from-image | Uses OCR to extract text from an image, including photos of documents. |
| Scan Barcode from Image | scan-barcode-from-image | Scans and reads barcodes and QR codes from an image, supporting multiple barcode formats including QR, EAN, UPC, and ... |
| Generate QR Code | generate-qr-code | Generates a QR code image from text or URL input. |
| Extract Entities from Text | extract-entities-from-text | Extracts named entities from text including people, organizations, locations, and other entity types. |
| Analyze Sentiment | analyze-sentiment | Analyzes text to determine sentiment, classifying it as Positive, Negative, or Neutral with a score from -1.0 to +1.0. |
| Resize Image Preserve Aspect Ratio | resize-image-preserve-aspect-ratio | Resizes an image while preserving its aspect ratio to fit within the specified maximum dimensions. |
| Resize Image | resize-image | Resizes an image to the specified width and height dimensions. |
| Detect Faces in Image | detect-faces-in-image | Detects and locates human faces in an image, returning bounding box coordinates for each face found. |
| Convert HTML to PDF | convert-html-to-pdf | Converts HTML content to PDF with full CSS, JavaScript, and image support for pixel-perfect rendering. |
| Convert PDF to DOCX | convert-pdf-to-docx | Converts a PDF document to editable Microsoft Word DOCX format with high fidelity. |
| Convert DOCX to PDF | convert-docx-to-pdf | Converts a Microsoft Word DOCX document to PDF format, preserving styling, footnotes, tables, and images. |
| Scan Website for Threats | scan-website-for-threats | Scans a website URL for malware, viruses, and phishing threats. |
| Advanced Virus Scan | advanced-virus-scan | Performs advanced virus scanning with additional threat detection including executables, scripts, macros, and passwor... |
| Scan File for Viruses | scan-file-for-viruses | Scans a file for viruses, malware, and other threats. |
| Geolocate IP Address | geolocate-ip-address | Returns geographic information for an IP address including country, region, city, and coordinates. |
| Validate URL | validate-url | Performs full validation of a URL including syntax check, domain verification, and threat detection. |
| Validate Email Address | validate-email-address | Performs full validation of an email address including syntax check, mail server verification, catch-all detection, a... |
membrane action run <actionId> --connectionId=CONNECTION_ID --jsonTo pass JSON parameters:
membrane action run <actionId> --connectionId=CONNECTION_ID --input '{"key": "value"}' --jsonThe result is in the output field of the response.
When the available actions don't cover your use case, you can send requests directly to the Cloudmersive API through Membrane's proxy. Membrane automatically appends the base URL to the path you provide and injects the correct authentication headers — including transparent credential refresh if they expire.
membrane request CONNECTION_ID /path/to/endpointCommon options:
| Flag | Description |
|---|---|
-X, --method | HTTP method (GET, POST, PUT, PATCH, DELETE). Defaults to GET |
-H, --header | Add a request header (repeatable), e.g. -H "Accept: application/json" |
-d, --data | Request body (string) |
--json | Shorthand to send a JSON body and set Content-Type: application/json |
--rawData | Send the body as-is without any processing |
--query | Query-string parameter (repeatable), e.g. --query "limit=10" |
--pathParam | Path parameter (repeatable), e.g. --pathParam "id=123" |
membrane action list --intent=QUERY (replace QUERY with your intent) to find existing actions before writing custom API calls. Pre-built actions handle pagination, field mapping, and edge cases that raw API calls miss.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.