consult-solution-planning
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external discovery artifacts and CRM data that may contain untrusted instructions.
- Ingestion points: Discovery summaries and pain point ledgers are read from Google Docs in Step 1, and existing deal notes are retrieved from the Zynkr CRM in Step 7.
- Boundary markers: The workflow does not specify the use of delimiters or 'ignore instructions' warnings when processing these external data sources.
- Capability inventory: The agent has the ability to create and update Google Docs, modify CRM deal notes, and create Gmail drafts based on the processed content.
- Sanitization: The instructions do not mention explicit sanitization or validation of the input data before it is interpolated into the planning framework.
Audit Metadata