kelly-insurance-intel
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources, creating a surface for indirect instructions to influence agent behavior.
- Ingestion points: The agent is instructed to browse and collect current public evidence from news sources, insurer announcements, regulator updates, and competitor pages (specified in
SKILL.mdandREADME.md). - Boundary markers: The instructions explicitly state that all signal, action, and draft collection must be held in a review gate within the Busabase app, requiring human approval before any external handoff occurs.
- Capability inventory: The skill has the capability to browse public websites and write records to a Busabase data store using the
busabase-sdk. - Sanitization: The UI code in
app.jsand the domain logic ininsurance-model.jsincludeescapeHtmlfunctions to sanitize data before rendering.
Audit Metadata