kelly-agent-observability
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it processes and displays user-submitted text that could contain malicious instructions.
- Ingestion points: Untrusted data enters the system through the handoff note form in
app.js, which is then stored in thehandoffsBusabase Base. - Boundary markers: The skill lacks explicit prompt boundary markers or instructions to the agent to ignore embedded commands when summarizing or reviewing handoff history.
- Capability inventory: The skill possesses the ability to write to the Busabase data layer and execute local scripts for data generation via the command line.
- Sanitization: While the application implements
escapeHtmlfor safe rendering in the browser, it does not sanitize the input for potential prompt-level instructions before the agent processes the data.
Audit Metadata