Back to skill

Security audit

Docx To Markdown

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward document-to-Markdown converter, but users should know it installs an external CLI and uploads documents to MinerU for processing.

Install only if you are comfortable using MinerU's external CLI and cloud processing. Avoid sending confidential documents unless MinerU's privacy terms meet your needs, and prefer installing the dependency in a low-privilege or sandboxed environment because the package versions are not pinned.

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:5
Finding
Unpinned Third-Party Executable Dependencies## Vulnerability Details **File Location**: `SKILL.md:5` **Vulnerability Type**: Unpinned third-party dependencies and mutable installation sources **Risk Level**: Medium ```yaml metadata: {"openclaw":{"emoji":"📑","requires":{"bins":["mineru-open-api"]},"install":[{"id":"npm","kind":"node","package":"mineru-open-api","bins":["mineru-open-api"],"label":"Install via npm"},{"id":"uv","kind":"uv","package":"mineru-open-api","bins":["mineru-open-api"],"label":"Install via uv"},{"id":"go","kind":"go","package":"github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api","bins":["mineru-open-api"],"label":"Install via go install","os":["darwin","linux"]}]}} ``` ### Technical Analysis The skill defines installation methods for the `mineru-open-api` executable through npm, uv, and Go without pinning a reviewed package version, immutable commit, or integrity checksum. Consequently, each installation may resolve to the latest mutable package or repository state rather than the exact artifact reviewed during the audit. The dependency's executable code is not included in this project, so its implementation cannot be verified from the audited artifact. If a package registry account, upstream repository, release process, or transitive dependency is compromised, a later installation could retrieve attacker-controlled code. There is no evidence in the audited file that the current upstream package is malicious; the finding concerns the absence of controls that bind installation to a known artifact. ### Attack Path 1. An attacker compromises the relevant package registry account, upstream repository, release pipeline, or a dependency used by `mineru-open-api`. 2. The attacker publishes a malicious release or modifies the mutable upstream source. 3. A user installs the skill dependency through one of the unpinned npm, uv, or Go installation definitions. 4. The package manager resolves and installs the attacker-controlled artifact because no ver ...[truncated 1050 chars]
Remediation
## Remediation Suggestions - Pin each installation method to a reviewed, immutable version rather than resolving the latest release. - For Go installation, use an audited semantic version or immutable commit identifier. - Use package-manager lockfiles and integrity hashes where the selected ecosystem supports them. - Verify package provenance, signatures, checksums, and publisher ownership before installation. - Prefer a single verified official distribution channel rather than offering several independently mutable sources. - Disable or review package installation scripts where practical, and perform installation without administrative privileges. - Execute the converter in a sandbox with minimal filesystem, credential, and network access. - Establish an update process that reviews and tests new dependency versions before changing the pinned artifact.
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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

Static analysis

No suspicious patterns detected.