good-html
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data from external sources, including code diffs, pull request comments, and incident reports, to generate formatted HTML dashboards.
- Ingestion points: User-provided content for "PR reviews," "code understanding," and "incident reports" as described in
references/page_types.md. - Boundary markers: The skill lacks instructions for using delimiters or boundary markers to separate the agent's instructions from the content being processed.
- Capability inventory: The skill generates HTML, CSS, and functional JavaScript logic and is instructed to write these to files (
SKILL.md). - Sanitization: There is no requirement in the workflow to sanitize or escape external content before it is interpolated into the HTML templates, which could lead to the agent following embedded instructions within the processed data.
- [DYNAMIC_EXECUTION]: The skill facilitates the generation of artifacts containing executable logic. This includes a "Radio State Engine" using CSS sibling selectors for interactivity and JavaScript snippets for features like clipboard management (
references/components.md). The capability to generate and execute interactive logic within artifacts is a core component of the skill's functionality.
Audit Metadata