lov-product-onepage
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill manages the poster creation lifecycle by instructing the agent to execute a provided CLI tool,
scripts/onepage_cli.py, for scaffolding projects and rendering images. - [EXTERNAL_DOWNLOADS]: The skill relies on the
playwrightPython library and thechromiumbrowser engine for its rendering engine. These are well-known, legitimate developer tools from a trusted organization. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input to generate marketing materials, representing a potential injection surface. 1. Ingestion points: Product briefs, conversation history, and URLs provided by the user (SKILL.md). 2. Boundary markers: The skill requires the agent to maintain a 'truth ledger' to distinguish between internal context and publishable claims (references/content-system.md). 3. Capability inventory: File system write operations, command-line execution of custom scripts, and headless browser automation (onepage_cli.py). 4. Sanitization: The project script uses
html.escape()to sanitize visible text copy during the HTML templating process (onepage_cli.py).
Audit Metadata