cro
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill analyzes external marketing pages via user-provided URLs, which serves as a vector for indirect prompt injection.
- Ingestion points: User-provided URLs for various page types (landing pages, pricing pages, forms) in SKILL.md.
- Boundary markers: Absent; there are no instructions to use delimiters or explicit directives to ignore instructions contained within the analyzed web content.
- Capability inventory: The skill environment allows for reading external web content and local context files such as .agents/product-marketing.md.
- Sanitization: The skill does not provide methods for sanitizing or filtering data retrieved from external URLs before processing.
Audit Metadata