bilt
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external API endpoints, which is a potential surface for indirect prompt injection.
- Ingestion points: Hotel and flight search data is retrieved from api.biltrewards.com via curl.
- Boundary markers: There are no specific delimiters or instructions provided to the agent to treat the API output as untrusted data.
- Capability inventory: The skill utilizes Bash(curl) and Bash(jq) to perform network requests and parse data.
- Sanitization: No explicit sanitization or validation of the API-returned content is performed before processing.
Audit Metadata