Back to skill

Security audit

Formula Ocr

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent formula OCR helper, but users should understand it depends on an external MinerU CLI/service and an API token.

Install only if you are comfortable using MinerU's third-party CLI/API for formula OCR. Avoid submitting confidential, regulated, or private documents unless that external processing is approved, prefer a pinned reviewed CLI version where possible, and keep MINERU_TOKEN limited to the process that needs it.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:15
Finding

Unpinned Third-Party CLI Installation

Content
View full analysis
Remediation
View remediation
go install github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api@ ``` 2. Prefer an immutable Go commit hash where practical, especially when reproducibility is required. 3. Publish expected checksums or signature-verification instructions for downloadable artifacts. 4. Document the exact package version that was security-reviewed and establish a controlled process for reviewing upgrades. 5. Avoid global npm installation where possible. Use a project-local dependency with a lockfile and integrity metadata, or run the tool inside a restricted container. 6. Disable or review npm lifecycle scripts when compatible with the package's installation requirements. 7. Run the CLI as an unprivileged user with access limited to required input and output paths. 8. Provide `MINERU_TOKEN` only to the process that requires it and avoid exposing unrelated credentials in the same execution environment. ]]>
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill advertises OCR for local files and URLs but does not clearly warn users that submitted documents or links may be transmitted to MinerU's external service and require a third-party API token. This creates a meaningful privacy and data-handling risk because users may provide sensitive PDFs, images, or URLs without informed consent about external processing.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The documentation states that the default language hint is ch and users must switch to en for English. This imposes a specific locale default in natural-language guidance without offering a neutral default or explaining why Chinese is mandated for this skill.

Content

No source excerpt is available for this finding.