Security audit

HTML Markdown

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward HTML-to-Markdown converter using MinerU, with some disclosed cloud/API and install risks users should understand before use.

Install only from a trusted MinerU source, prefer a pinned version or isolated environment, and treat any HTML file or URL you convert as potentially sent to MinerU's service. Use a limited MinerU token and do not submit sensitive internal pages unless that is approved.

A.I.G

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:14
Finding: Unpinned Third-Party CLI Installation
Content: View full analysis
Remediation: View remediation

SkillSpector

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 explicitly supports remote URLs and requires an API token, which implies user-supplied URLs and fetched content are processed by the external MinerU service. Failing to disclose that remote page URLs and potentially page content are transmitted off-host creates a real privacy and data-handling risk, especially if users convert internal, sensitive, or access-controlled pages assuming processing is local.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The natural-language note states --language defaults to ch and suggests en for English, which imposes a locale/language default in the skill documentation. There is no accompanying opt-in choice or explanation that this skill is region-specific, so it may conflict with language/locale policy expectations.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.