enrichment-design
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from external, untrusted sources such as job postings, LinkedIn profiles, and news articles.
- Ingestion points: The enrichment design logic in SKILL.md identifies signal sources like LinkedIn, job boards, and news sites as primary data providers for agent research.
- Boundary markers: The provided templates for queries to backends like 'Clay' and 'Account Researcher' do not include delimiters or explicit instructions for the agent to disregard potential commands embedded in the fetched content.
- Capability inventory: The output configurations are designed to be consumed by downstream tools like 'list-enrichment' and 'email-prompt-building', which perform automated actions based on the retrieved data.
- Sanitization: The skill does not define any sanitization, filtering, or validation steps for the content returned from external research backends before it is interpolated into agent prompts.
Audit Metadata