nurture-value-factory
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from user briefs and existing company documents to generate asset specifications and route them to various downstream build tools.
- Ingestion points: Data enters the skill via the user's brief and company documents (ICP, GTM audit, offers, earlier sequences, design system) as described in Step 0.
- Boundary markers: The instructions do not define explicit delimiters or instructions to ignore potential commands embedded within the ingested documents.
- Capability inventory: The skill has the capability to invoke and pass parameters to numerous other agent skills, including
docx,xlsx,free-tools,lead-magnets,page-builder, andwebsite-copy-reframe(Step 5). - Sanitization: While it mentions editing prose for "AI tells" and using
anticopywriting-ai, there is no evidence of structural validation or sanitization of the input data to prevent injection attacks.
Audit Metadata