The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill provides patterns for processing external data from HTTP requests (JSON bodies, path parameters, query strings, and headers). While this introduces a potential attack surface for indirect prompt injection, the skill mitigates this by recommending strict schema validation using the @hono/zod-validator middleware as a core best practice.
Ingestion points: c.req.param, c.req.query, c.req.header, and c.req.json in SKILL.md.
Boundary markers: Explicit instructions to use zValidator with Zod schemas to define data boundaries.
Capability inventory: No dangerous capabilities like arbitrary shell execution or file system writes are used in the provided examples; operations are limited to standard web routing and response handling.
Sanitization: Recommends the use of Zod schemas for mandatory input validation and type enforcement.

hono-idioms