html-express
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides a collection of CSS design tokens and HTML component templates (e.g., metric cards, comparison tables) to facilitate the creation of structured reports. The assets are static and do not include executable scripts, network calls, or file system modifications.
- [NO_CODE]: No executable code, such as Python scripts or binaries, is distributed with this skill; it consists entirely of configuration and presentation templates.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to transform dense information into a visual HTML format, which introduces a surface for indirect prompt injection if the processed data contains malicious instructions.
- Ingestion points: External information processed by the agent into the HTML components as described in SKILL.md.
- Boundary markers: Absent; no specific delimiters or warnings for embedded instructions are provided in the templates.
- Capability inventory: The skill guides the agent to generate a local .html file (file-write capability) using the structure defined in SKILL.md and assets/skeleton.html.
- Sanitization: Absent; no explicit sanitization or filtering of external content is defined within the provided assets.
Audit Metadata