weekly-business-report
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: Potential surface for indirect prompt injection via ingested business data.
- Ingestion points: External systems including Supabase, CRM, support tickets, and custom APIs as listed in
references/data-and-calculations.md. - Boundary markers: None present to distinguish untrusted text data from system instructions.
- Capability inventory: The skill allows execution of tools including
Read,Write,Bash,Glob,Grep, andWebSearchspecified inSKILL.md. - Sanitization: No validation or escaping mechanisms are implemented for ingested text fields.
Audit Metadata