skills/agentskillexchange/skills/Turn Markdown or raw content into agent-generated HTML artifacts with HTML Anything/Gen Agent Trust Hub
Turn Markdown or raw content into agent-generated HTML artifacts with HTML Anything
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data (Markdown or raw content) to generate HTML artifacts. This workflow introduces a potential surface where malicious instructions embedded in the source data could influence the agent's behavior during the generation process.
- Ingestion points: Raw content and Markdown files provided to the agent (referenced in SKILL.md description).
- Boundary markers: None defined within the skill instructions to delimit untrusted content.
- Capability inventory: HTML artifact generation, streaming to preview, and asset export (SKILL.md).
- Sanitization: No sanitization or filtering mechanisms are described in the skill metadata.
- [NO_CODE]: The provided skill file lacks executable code, configuration for specific tool invocations, or functional instructions for the agent. It serves primarily as metadata and documentation for an external project.
Audit Metadata