bun-hono-integration
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for initializing a project using
bun create hono, which involves downloading template files from official sources. This is standard framework behavior for project setup. - [INDIRECT_PROMPT_INJECTION]: The skill establishes patterns for ingesting untrusted data through various HTTP request methods such as query strings and request bodies. This creates a potential surface for indirect prompt injection if the data is eventually passed to a language model. However, the skill provides mitigation strategies via integrated validation.
- Ingestion points: The handlers documented in
SKILL.mdprocess external inputs viac.req.json,c.req.query, and path parameters. - Boundary markers: The skill does not provide LLM-specific boundary markers but focuses on schema-level validation.
- Capability inventory: The snippets demonstrate standard web server capabilities for request routing and response handling.
- Sanitization: The documentation includes specific examples of using
@hono/zod-validatorfor defining and enforcing schemas on incoming untrusted data.
Audit Metadata