html-mail-builder
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script (
scripts/generate_email_template.py) to process user-provided JSON configuration files and generate HTML output. This is the primary function of the tool and is executed within the local environment. - [PROMPT_INJECTION]: The skill processes untrusted data to generate content, creating a surface for indirect prompt injection. \n
- Ingestion points: Data is gathered from user requests or external context and written to a
config.jsonfile. \n - Boundary markers: There are no explicit instructions or delimiters used to warn the agent about ignoring embedded instructions in the processed data. \n
- Capability inventory: The skill uses a local script with file-system write access to produce the final template. \n
- Sanitization: While the Python script correctly applies
html.escape()to text content (names, messages, labels), it does not sanitize theme variables such asprimary_colororfont_family. These values are inserted directly into HTML style attributes, potentially allowing for CSS injection or data tracking (e.g., via background images) in the generated templates.
Audit Metadata