landing-page-cro-expert
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill involves processing external data that could contain hidden instructions meant to manipulate the agent's analysis or behavior.
- Ingestion points: Landing page URLs and screenshots provided by users for evaluation (SKILL.md).
- Boundary markers: Absent; there are no specific delimiters or instructions defined to isolate the external content from the skill's logical prompts.
- Capability inventory: The skill relies on the agent's baseline text processing and does not execute custom scripts or perform privileged network/file operations.
- Sanitization: Absent; the skill does not specify any validation or cleaning steps for the data retrieved from external landing pages.
Audit Metadata