Mistral PDF OCR

PassAudited by ClawScan on May 1, 2026.

Overview

This skill is a coherent Mistral OCR integration, but users should know it sends selected documents to Mistral, uses a Mistral API key, and writes full OCR outputs locally.

Before installing, confirm you are comfortable sending the chosen PDFs or images to Mistral, keep your Mistral API key secure, and store or delete the generated OCR output files according to the sensitivity of the documents.

Findings (5)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

Private or sensitive PDFs/images may be uploaded to Mistral for processing.

Why it was flagged

Local documents are intentionally sent to the external Mistral API for OCR. This is central to the skill, but users should understand that document contents leave the local environment.

Skill content
If the PDF is local and not publicly accessible, upload it (the script does this automatically).
Recommendation

Use this only for documents you are allowed to send to Mistral, consider page selection for large or sensitive files, and review Mistral retention/privacy terms.

What this means

Anyone running the skill needs a valid Mistral API key, and OCR requests may be billed to that account.

Why it was flagged

The script uses a Mistral API key from the environment. This is expected for the Mistral OCR service, but it grants access to the user's Mistral account and may incur usage costs.

Skill content
api_key = os.getenv("MISTRAL_API_KEY")
Recommendation

Store the API key securely, use the least-privileged key available, and avoid exposing environment variables in logs or shared shells.

What this means

The agent can run the OCR Python script and create output files in the chosen directory.

Why it was flagged

The skill permits running Python commands and writing output files. This is proportionate for a bundled OCR script, but it is still local command execution.

Skill content
allowed-tools: "Read,Write,Bash(python:*)"
Recommendation

Run it only on intended input files and direct outputs to a safe, expected folder.

What this means

A future SDK version could behave differently from the version the skill author tested.

Why it was flagged

The skill depends on the external mistralai package using a lower-bound version rather than an exact pinned version. This is common for SDK integrations but can change behavior as new package versions are installed.

Skill content
mistralai>=1.0.0
Recommendation

Install dependencies from trusted package sources and consider pinning a known-good mistralai version in controlled environments.

What this means

OCR outputs may create persistent local copies of sensitive document content.

Why it was flagged

The skill stores the full OCR response locally, which may include extracted text, tables, annotations, and image data from the source document.

Skill content
raw_response.json (full OCR response)
Recommendation

Store the output directory securely and delete OCR artifacts when they are no longer needed.