landing-page-generator
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to execute bundled Python scripts (
scripts/cta_analyzer.py,scripts/conversion_checklist.py, andscripts/page_speed_estimator.py) to perform audits on HTML files. These scripts are diagnostic in nature, limited to regex-based parsing, and do not utilize unsafe modules or external dependencies. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface by analyzing HTML files that may contain untrusted content.
- Ingestion points: The audit scripts in the
scripts/directory read the content of user-provided HTML files (e.g.,page.html). - Boundary markers: None. The scripts process the raw HTML and output findings directly to the console.
- Capability inventory: The scripts are restricted to text processing via the
remodule and lack network access, file-writing permissions, or dynamic execution capabilities (evalorexec). - Sanitization: No sanitization is performed on the input HTML, as the scripts only scan for specific tags and attributes without executing the content.
Audit Metadata