shunk031-writing-router

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references several external GitHub repositories belonging to third-party developers (iwasa-kosui/tanteki, coji/natural-japanese, nanaism/yomiyasu) to provide specialized writing functionality.
  • [COMMAND_EXECUTION]: Provides a specific shell command (gh skill install iwasa-kosui/tanteki ...) for the agent to share with the user if a required dependency is not found. The instructions explicitly state that the agent must not install the skill without the user's request or pretend the skill is already used.
  • [PROMPT_INJECTION]: Includes a confirmation prompt in the SKILL.md file that instructs the agent to output a specific emoji-prefixed string ("✍️ 私は shunk031-writing-router を読みました。") immediately after reading the instructions. While this is a behavioral override, it is a common pattern for verifying system prompt adoption and does not exhibit malicious intent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 03:24 PM