markitdown
Convert heterogeneous documents and selected URIs to Markdown with Microsoft MarkItDown for text analysis, search, and LLM/RAG ingestion. Covers safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server.
66
79%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Fix and improve this skill with Tessl
tessl review fix ./skills/markitdown/SKILL.mdSecurity
1 critical severity finding. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E005: Suspicious download URL detected in skill instructions.
What this means
Detected a suspicious URL in the skill instructions that could lead the agent to download and execute malicious scripts or binaries. This includes links to executables from untrusted sources, typosquatting of official packages, URL shorteners that obscure the destination, and personal file hosting services.
Why it was flagged
The listed http://127.0.0.1:3001/sse and http://127.0.0.1:3001/mcp endpoints are potentially risky because they refer to an unauthenticated local MCP HTTP/SSE server (markitdown-mcp) that can accept arbitrary URIs and serve or fetch content on the local host, making them a plausible vector to distribute or trigger execution of malicious payloads via SSRF/localhost access.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The required runtime workflow ingests outsider-authored free text when it converts application-facing uploaded bytes via `convert_stream()`/`convert_response()` and then returns `result.markdown` for LLM ingestion (e.g., “Binary Upload” and “Application-Controlled Remote Resource” workflows).
- Repository
- K-Dense-AI/scientific-agent-skills
- Commit
b2a92ba
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.