navan-prod-checklist
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data retrieved from the Navan API, creating a potential surface for indirect prompt injection attacks if the API response contains malicious instructions.
- Ingestion points: The
SKILL.mdfile contains bash commands that fetch user data fromhttps://api.navan.com/v1/usersand authentication tokens fromhttps://api.navan.com/ta-auth/oauth/token. - Boundary markers: The skill does not explicitly use delimiters or specific instructions to the agent to ignore potentially malicious content embedded in the API responses.
- Capability inventory: The skill is authorized to use
Write,Edit,Bash(curl), andBash(jq)tools, which could be leveraged if an injection succeeds. - Sanitization: No sanitization or validation of the API response data is performed before it is processed by
jqor read by the agent.
Audit Metadata