md-to-html
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted Markdown content which could contain hidden instructions intended to influence the agent's behavior.
- Ingestion points: Processes Markdown content from input strings or existing files to generate HTML and wiki entries.
- Boundary markers: Absent. The instructions do not define delimiters or specific "ignore" instructions for the agent to use when processing the source Markdown.
- Capability inventory: The skill has the capability to create and modify files within the local filesystem (specifically the
html/andllmwiki/directories). - Sanitization: No explicit sanitization or escaping of the input Markdown is specified before it is rendered or logged into the wiki files.
Audit Metadata