SKILLEMALL.ai
GitHub ↗ RU Sign in

CD sm-ocr-scanner

Lokale OCR für Rasterbilder (jpg, png, bmp, gif, tiff, webp) und PDF-Dateien mit dem systemeigenen tesseract-Binary. PDF-Seiten werden lokal mit pdftoppm gerastert, vorhandene PDF-Textlayer mit pdftotext gelesen. Ausgabe als Klartext, TSV mit Konfidenzwerten oder durchsuchbares PDF. Die OCR läuft ohne Netzwerkverbindung, ohne Cloud-Dienst und ohne API-Key. Nur der optionale, vom Nutzer gestartete Installer lädt Abhängigkeiten über den Paketmanager der Distribution (optional PyPI mit --allow-pip); Systempakete installiert er nur, wenn der Nutzer ihn selbst als root startet, und erst nach Bestätigung am Paketmanager. Das Paket enthält nur Text.

ClawHub Agent Skills author: kaarl92 v1.2.2 MIT-0 8 files · 3 scripts body ≈ 4 772 tokens Open the sourceclawhub.ai↗ analyzed 5 d ago

Lokale OCR für Rasterbilder (jpg, png, bmp, gif, tiff, webp) und PDF-Dateien mit dem systemeigenen tesseract-Binary.

As a process D 36/100 · Unfinished process — References files that are not bundled: assets/tessdata/

IntegrationAI and agentsWriting and documentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
C
79/100
safety, quality, tests
Safety 60%
88
Quality 40%
66
Run on models
none yet
Process rating
D
36/100
Unfinished process
References files that are not bundled: assets/tessdata/
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 4

✓ No critical or high findings

Medium and low: 4
  • medium Dangerous commands cmd-privilege scripts/install.sh:81
    Privilege escalation / world-writable permissions
    sudo bash scripts/install.sh                     # Systeminstallation (fragt nach)
  • medium Dangerous commands cmd-privilege scripts/install.sh:253
    Privilege escalation / world-writable permissions
    Systeminstallation bewusst als root starten:  sudo bash scripts/install.sh" 2
  • low Dangerous commands cmd-privilege SKILL.md:140
    Privilege escalation / world-writable permissions (documentation of a security skill)
    sudo bash scripts/install.sh
    security skill
  • low Dangerous commands cmd-privilege SKILL.md:152
    Privilege escalation / world-writable permissions (documentation of a security skill)
    sudo bash scripts/install.sh --lang "deu eng fra ita"
    security skill

Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: assets/tessdata/

Process rating: all ten parameters 36/100

Will not run. References files that are not bundled: assets/tessdata/
  • 0Tools and files. 1 referenced file(s) missing: assets/tessdata/
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 50Failures and branches. 0 branches, has a failure section
  • 70Execution cost. Instruction body is 4772 tokens
  • 85Steps. 57 steps, 1 vague phrases
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • low 13 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (5 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -41 reference files, but SKILL.md never points to them: the model will not open them
  • +2Single-language instructions
  • +3Description length 650: enough signal without eating the budget
  • +4Structure: 17 headings
  • +3Step-by-step instructions: 57 items
  • +4Has examples (4 code blocks)
  • +3All 3 scripts are documented
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.

External checks

ClawHub: clean
This is a coherent local OCR skill with disclosed, user-controlled installation options and no evidence of hidden data sharing or unsafe automatic behavior.
LLM: benign (high) · VirusTotal: · 4 Oct 2026