gtm-market-icp-persona
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources and processes it through an agent context without sanitization.
- Ingestion points: Reads client-provided "Snapshot" and "Stage" data from Notion pages as the basis for analysis.
- Boundary markers: The instructions lack specific delimiters or "ignore instructions" warnings to separate user-provided data from system instructions.
- Capability inventory: The skill utilizes the ability to write generated GTM strategies, market scores, and buyer personas to new Notion pages.
- Sanitization: No filtering or validation logic is defined to prevent instructions embedded within the Notion Snapshot from influencing the agent's behavior.
Audit Metadata