kelly-ai-newsroom
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external news sources, creating an ingestion surface for untrusted data. However, the skill explicitly enforces a 'gated-write' boundary where all generated signals, actions, and drafts must be manually reviewed and approved by a human in the provided cockpit UI before any external execution occurs.
- [COMMAND_EXECUTION]: The skill includes maintenance and execution scripts (e.g.,
execute_decisions.mjs,setup.mjs). These scripts use the officialbusabase-sdkand rely on standard environment variables for authentication, which is a secure practice for this platform's architecture. They do not execute arbitrary or unsanitized user commands. - [EXTERNAL_DOWNLOADS]: Dependencies are restricted to well-known and relevant packages such as
busabase-sdk,hono, andesbuild-wasm. No unauthorized remote script execution or 'curl | bash' patterns were found.
Audit Metadata