gtm-offers
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from Notion to generate business offers, creating a potential for indirect prompt injection.
- Ingestion points: Market research and persona data are read from Notion steps 3-7.
- Boundary markers: The skill lacks explicit data delimiters or instructions to disregard embedded commands in the source data.
- Capability inventory: The skill is capable of reading from and writing to the user's Notion workspace.
- Sanitization: No sanitization or content validation is performed on the ingested data.
Audit Metadata