duffel
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes live flight data from the Duffel API, which introduces an ingestion point for untrusted content that could theoretically contain hidden instructions.
- Ingestion points: API responses from
https://api.duffel.com/air/offer_requests. - Boundary markers: No delimiters or ignore instructions are used to separate API data from the agent's context.
- Capability inventory: The skill uses
Bash(curl)andjqto fetch and parse results. - Sanitization: No sanitization or filtering of the API content is performed.
- [EXTERNAL_DOWNLOADS]: The skill fetches flight offers and pricing from the Duffel API service.
- [COMMAND_EXECUTION]: Uses
curlto perform authenticated network operations against the flight search API.
Audit Metadata