document-converter

Pass

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external documents, which may contain hidden instructions intended to influence the AI's behavior.\n
  • Ingestion points: Local files and remote URLs converted via the convert_to_markdown tool and the CLI as described in SKILL.md.\n
  • Boundary markers: None specified; there are no instructions to the agent to treat extracted content as untrusted or to ignore embedded commands.\n
  • Capability inventory: Uses shell command execution and local file read access to process documents.\n
  • Sanitization: There is no description of content sanitization or validation during the conversion process.\n- [EXTERNAL_DOWNLOADS]: Fetches and installs the markitdown and markitdown-mcp packages from PyPI to enable document conversion.\n- [COMMAND_EXECUTION]: Provides detailed instructions for the agent to run the markitdown command-line utility for local processing.\n- [DATA_EXFILTRATION]: The conversion tool includes native functionality to download and process document content from remote HTTP/HTTPS URLs.
Audit Metadata
Risk Level
SAFE
Analyzed
May 8, 2026, 07:17 AM
Security Audit — agent-trust-hub — document-converter