mcp
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides documentation for the
html-to-markdown-rsModel Context Protocol tools. - [INDIRECT_PROMPT_INJECTION]: The skill documents tools that ingest and process external HTML data, which represents an attack surface for indirect prompt injection.
- Ingestion points: The
convert_htmlandextract_metadatatools process HTML input in SKILL.md. - Boundary markers: No delimiters or ignore instructions are specified for external content.
- Capability inventory: The tools perform HTML parsing and structured data extraction. No subprocess calls, file-write, or network operations are documented in the skill instructions.
- Sanitization: No sanitization or filtering logic is documented for the external HTML content.
Audit Metadata