querying-well-data
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external workspace data (such as invoices, bank transactions, and accounting ledgers), which represents a theoretical surface for indirect prompt injection if the retrieved records contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The agent retrieves data through the
well_query_recordsandwell_get_entitytools described inSKILL.md. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore instructions embedded within the retrieved financial records.
- Capability inventory: The skill provides access to read financial schemas and records via MCP tools (
well_get_schema,well_query_records,well_get_entity). - Sanitization: There are no explicit instructions for the agent to sanitize or validate the content of the records before processing them.
Audit Metadata