markitdown
What this skill does
Document conversion to Markdown for text analysis, search, and LLM/RAG ingestion
github/k-dense-ai - Security Misconfiguration - 33.1k stars
Threat analysis
Skill info
pkg:github/K-Dense-AI/scientific-agent-skills@3956e54?skill=markitdownAssessments (3)
Security Misconfiguration
Security Misconfiguration via local-llm-review
references/mcp_and_plugins.md
The MCP server has no authentication and runs with the current user's privileges. It can read files accessible to that user through file: URIs and fetch network resources accessible to that process. ISecurity Misconfiguration via local-llm-review
references/security.md
The API `convert_uri()` accepts file:, data:, http:, and https: URIs with no built-in application allowlist, which could allow arbitrary file access or SSRF attacks.Security Misconfiguration via local-llm-review
references/cloud_and_ocr.md
The built-in image description feature calls an OpenAI-compatible client with image bytes encoded as a data URI, which could potentially expose sensitive image data to external services.Badge
Add the Anomity scan badge for markitdown to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of markitdown? Report an issue or request a rescan.
