landing-page-generator
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted product descriptions and brand content to generate marketing copy and code components, creating a surface where malicious instructions embedded in the input could influence the generated output.
- Ingestion points: Generation Workflow Step 1 (product name, tagline, audience, pain point) and Step 2 (brand content analysis) in
SKILL.md. - Boundary markers: The instructions in
SKILL.mddo not define delimiters (e.g., XML tags or triple backticks) to isolate untrusted data, nor do they instruct the agent to ignore potentially malicious instructions embedded in the provided data. - Capability inventory: The skill possesses file-writing capabilities via the
landing_page_scaffolder.pyscript and the agent's native file-handling tools. - Sanitization: The
landing_page_scaffolder.pyscript correctly usesjson.dumpsandhtml.escapeto sanitize content and validates URL schemes intsx_href. However, the prompt instructions for the agent to "Output final components" do not explicitly mandate these sanitization steps if the agent generates the TSX directly without the script.
Audit Metadata