convert-documents-to-markdown

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx -y @firecrawl/anydoc to download and execute the conversion package directly from the NPM registry at runtime.
  • [COMMAND_EXECUTION]: Instructions direct the agent to execute shell commands using npx to perform document conversions and write output to the filesystem (e.g., npx -y @firecrawl/anydoc <file> -o out.md).
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process various external document formats which may contain untrusted data.
  • Ingestion points: Local files including .doc, .pdf, .xls, and .epub are read and converted to text (SKILL.md).
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings for the converted output.
  • Capability inventory: The skill has the capability to write converted content to new files using the -o flag.
  • Sanitization: There is no mention of sanitization or filtering of the content extracted from the documents before it is presented to the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 12:59 AM
Security Audit — agent-trust-hub — convert-documents-to-markdown