cro
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 web pages and marketing materials, which is an attack surface for instructions hidden within that data.
- Ingestion points: The skill analyzes URLs and content of marketing pages, forms, and checkout flows as specified in SKILL.md.
- Boundary markers: There are no instructions to use delimiters or ignore embedded instructions when the agent processes external content.
- Capability inventory: The skill is primarily analytical but references related capabilities like A/B testing, analytics, and CRM integration (SKILL.md).
- Sanitization: No sanitization or validation of the ingested external content is mentioned in the analysis framework.
Audit Metadata