waterfall-enrichment
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 such as company domains and LinkedIn URLs to facilitate enrichment tasks via external services.
- Ingestion points: The skill accepts user-provided domains and LinkedIn profile URLs as primary inputs for enrichment cascades.
- Boundary markers: There are no explicit instructions or delimiters defined to prevent the AI from interpreting malicious instructions that might be embedded in the input data.
- Capability inventory: The skill is designed to interact with external tools and APIs, including the apolloFindPeople workflow node and various third-party email finders.
- Sanitization: No sanitization or validation steps are mentioned for the incoming data before it is passed to secondary tools or used in decision-making.
Audit Metadata