Sm Ocr Scanner

Perform OCR on image files (jpg, png, bmp, gif, tiff) using the system's `tesseract` binary and return extracted plain text.

Security Scan

The skill mostly matches an on‑host tesseract OCR wrapper, but it includes an undocumented networked example (uploads images to ocr.space using a hardcoded demo key) and fails to declare required binaries, so the package contains capabilities not described in the SKILL.md.

Purpose & Capability

The skill's name and SKILL.md describe a local tesseract OCR wrapper, which matches scripts/ocr.sh (uses tesseract and pdftoppm). However the package also includes scripts/example.py that calls the external OCR.space API (network I/O) using a hardcoded demo key; this external-call capability is not documented or declared in the SKILL.md or registry metadata. Also the metadata claims no required binaries while the wrapper requires tesseract and pdftoppm — an omission that reduces transparency.

Instruction Scope

SKILL.md instructs running the local Bash wrapper (ocr.sh) only; it does not mention the example Python script that will POST images to an external service. The Python example will read local image files and transmit them to api.ocr.space (possible data exfiltration) — this network behavior is not disclosed in the runtime instructions.

Install Mechanism

There is no install spec (instruction-only); nothing is automatically downloaded or installed. The risk from install mechanisms is low because no archive downloads or package installs are specified.

Credentials

The skill requests no environment variables or credentials. The included example script contains a hardcoded public demo API key ('helloworld') for ocr.space — not a secret, but it means the example may rely on an external service. No other credentials are present or requested.

Persistence & Privilege

The skill is not always-enabled and is user-invocable; it does not request elevated privileges or try to modify other skills or global agent settings.

What to consider before installing

Before installing or running this skill: (1) Understand which script you'll use — scripts/ocr.sh runs local tesseract/pdftoppm and does not contact remote services; scripts/example.py will upload images to api.ocr.space using a demo API key. (2) If you only want local OCR, avoid running example.py or inspect/disable it. (3) Verify the required binaries are present (tesseract, pdftoppm) and that you are comfortable granting the skill access to any image files you pass it. (4) Do not process sensitive images with the example.py uploader unless you accept that the image will be sent to a third‑party service. (5) Consider removing or sandboxing the Python example if you want to eliminate unintended network exposure.

sm-ocr-scanner (funktionierender Skill)

Überblick

Dieser Skill nutzt das lokale Tesseract‑OCR‑Programm, um Text aus gängigen Bildformaten zu extrahieren. Er ist sofort einsetzbar, weil tesseract bereits auf dem System installiert ist.

Verwendung

# Aufruf über das Skill‑Skript (empfohlen)
~/.openclaw/workspace/skills/sm-ocr-scanner/scripts/ocr.sh <Pfad‑zur‑Bilddatei>

Beispiel:

~/.openclaw/workspace/skills/sm-ocr-scanner/scripts/ocr.sh /root/.openclaw/media/inbound/916f6187-cc22-4c62-bcfc-7b72198c8a10.png

Der erkannte Text wird auf STDOUT ausgegeben.

Optionen

• Der Aufruf nutzt -l eng, um die englische Sprachdatei zu erzwingen. Für andere Sprachen kannst du das Flag anpassen, z. B. -l deu für Deutsch.
• Wenn du die Sprache automatisch erkennen lassen möchtest, entferne das -l‑Flag.

Integration in OpenClaw (optional)

Falls du den Skill später über das OpenClaw‑CLI ausführen willst, kannst du einen Alias in deiner ~/.bashrc (oder ~/.zshrc) hinzufügen:

alias sm-ocr-scanner='~/.openclaw/workspace/skills/sm-ocr-scanner/scripts/ocr.sh'

Dann kannst du einfach ocr-image <datei> tippen.

Hinweis

Der ursprüngliche Platzhalter‑Skill war nicht funktionsfähig. Durch das Hinzufügen dieses Bash‑Wrappers wird er zu einem echten OCR‑Tool, das sofort einsatzbereit ist.