10-materials-plan
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection as it processes untrusted data from external sources. * Ingestion points: Reads ICP, positioning, and buyer journey data from Notion (referenced in argument-hint). * Boundary markers: The instructions lack delimiters or explicit directives to ignore embedded instructions in the source data. * Capability inventory: The skill has the ability to write new pages and tables to Notion. * Sanitization: No sanitization, validation, or escaping of the ingested Notion content is defined.
Audit Metadata