navan-data-handling
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides patterns for ingesting untrusted data from the Navan API (
v1/bookings) which may contain malicious instructions. \n- Ingestion points: API response data processed inSKILL.mdsnippets. \n- Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore embedded instructions in the fetched data. \n- Capability inventory: The skill utilizesfetch,requests, and has access toBash(npm, curl, pip) for processing data. \n- Sanitization: No evidence of data sanitization or validation was found in the provided processing scripts.
Audit Metadata