bx-markdown
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted Markdown and HTML data, which represents an attack surface for indirect prompt injection where instructions embedded in the data could attempt to influence the agent.
- Ingestion points: The
markdown()andHtmlToMarkdown()functions accept string inputs that the documentation shows being sourced from database queries (queryExecute) and file reads (fileRead) in SKILL.md. - Boundary markers: No specific delimiters or instructions are provided to the agent to treat the processed data as untrusted content.
- Capability inventory: The skill provides text conversion capabilities between Markdown and HTML formats.
- Sanitization: The documentation proactively addresses security by advising users not to output user-provided markdown directly and suggests using
bx-jsoupfor XSS protection. - [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing the
bx-markdownmodule viainstall-bx-moduleand the CommandBox CLI. These operations fetch the module from the vendor's official package repository.
Audit Metadata