The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and modifies local source code to enforce Hono architecture rules. This creates a potential attack surface where instructions embedded in the analyzed codebase (e.g., in comments or string literals) could influence the agent's behavior during remediation tasks.
Ingestion points: The workflow involves scanning and reading files within the src, app, and routes directories using rg (ripgrep).
Capability inventory: The agent has the ability to read files, search contents, and perform modifications such as renaming files and editing source code for auto-remediation (e.g., moving database calls, adding middleware).
Boundary markers: There are no explicit instructions to use boundary markers or delimiters to isolate the codebase content from the agent's internal reasoning process.
Sanitization: The skill does not describe any specific sanitization, filtering, or validation of the codebase content before it is interpolated into the agent's context.

hono-architecture