flexport-hello-world
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the Flexport API, creating an attack surface where untrusted external content could potentially influence the agent's behavior.
- Ingestion points: The code examples in
SKILL.md(TypeScript, Python, and cURL) fetch data from thehttps://api.flexport.comendpoint. - Boundary markers: The skill does not implement delimiters or explicit instructions for the agent to ignore potential commands embedded within the API response data.
- Capability inventory: The skill environment is configured with
Bash,Write, andEdittools, which could be leveraged if an injection occurred. - Sanitization: There is no evidence of data sanitization or validation for the fields returned by the API (such as shipment statuses or port names) before they are processed.
Audit Metadata