landing-page-copywriting
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data provided by the user, such as existing landing page copy or website URLs (Section 8), which constitutes a surface for indirect prompt injection attacks where the external content might contain instructions to hijack the agent.
- Ingestion points: User-provided product descriptions, existing conversion copy, and website URLs in SKILL.md (Sections 1, 3, and 8).
- Boundary markers: The instructions do not define clear delimiters or specify that the agent should ignore instructions embedded within the provided data.
- Capability inventory: The skill uses standard agent capabilities to read and write text. While the skill does not explicitly call tools, the workflow involves processing external text that could influence downstream agent logic.
- Sanitization: There are no instructions for sanitizing or escaping the content retrieved from external sources before it is processed by the agent.
Audit Metadata