markitdown
Convert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more.
Security
2 findings: 1 high severity, 1 medium severity. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill includes code examples that put API keys directly into string literals (e.g., api_key="your-openrouter-api-key"), which encourages embedding secrets verbatim in generated code/commands and therefore would require the LLM to handle/output secret values directly.
W013: Attempt to modify system services in skill instructions.
What this means
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
Why it was flagged
The skill documentation explicitly instructs using "sudo apt-get install tesseract-ocr", which asks the agent/user to obtain elevated (sudo) privileges to modify the system, so it could push the agent to compromise machine state.
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 (e.g., `scripts/convert_literature.py` and `scripts/batch_convert.py`) ingests the user-supplied converted document text (`result.text_content`)—which can include outsider-authored free text from PDFs/DOCs/HTML/images/YouTube/transcripts located outside the operating user’s authorship—into the generated Markdown that is then handled by the agent/LLM pipeline.
- Repository
- synthetic-sciences/openscience
- Commit
dc00e07
- 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.