hono
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill uses imperative and forceful language to override the agent's default behavior. Evidence includes instructions like "CRITICAL: Your training data for Hono is unreliable", "you MUST use WebFetch", and "Do not proceed without fetching this URL first".
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest external data which could potentially contain malicious instructions.
- Ingestion points: The agent is instructed to fetch content from
https://hono.dev/llms.txtusing theWebFetchtool. - Boundary markers: There are no boundary markers or instructions to ignore embedded commands within the fetched content.
- Capability inventory: The agent typically has capabilities including file system access and shell command execution.
- Sanitization: No sanitization or validation of the fetched remote content is described.
- [EXTERNAL_DOWNLOADS]: The skill fetches live documentation from the official Hono framework website (hono.dev) to ensure up-to-date API information.
Audit Metadata