skills/da1z/agent-things/hono/Gen Agent Trust Hub

hono

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill instructs the agent to ingest external content from hono search results and the web URL https://hono.dev/llms.txt.
  • Ingestion points: CLI output from the hono search command and the content of the llms.txt file at hono.dev.
  • Boundary markers: None present in the prompt instructions to delineate external content.
  • Capability inventory: Displaying and processing documentation content for the user.
  • Sanitization: None provided; the agent relies on the content being safe.
  • [External Downloads] (INFO): The skill references a remote documentation index at https://hono.dev/llms.txt. This is a trusted domain for the Hono framework.
  • [Command Execution] (LOW): The skill utilizes the hono CLI tool. While it uses standard documentation commands, it assumes the environment has the tool pre-installed or allows its execution.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 09:04 AM