nurture-architect
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data sources which may contain untrusted content.
- Ingestion points: In
SKILL.md(Step 0), the agent is instructed to load external inputs including ICP (Ideal Customer Profile) documents, GTM (Go-To-Market) audits, existing offers, and previous communication sequences. - Boundary markers: The instructions do not specify the use of clear delimiters or boundary markers when interpolating these external data sources into the agent's context.
- Capability inventory: The skill possesses the capability to write files (Notion, markdown, or .docx) and invoke other tools such as
nurture-value-factory,cta-interest-based, andsequence-writer. - Sanitization: While the skill contains "Hard rules" to avoid inventing data and to maintain confidentiality, there is no explicit instruction for the agent to sanitize or ignore potentially malicious instructions embedded within the ingested lead magnets, audits, or sequences.
Audit Metadata