translate-readme-and-skills

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is restricted to translating specific markdown files (README.zh-CN.md and locale files). It does not request network access or the ability to run arbitrary code.
  • [COMMAND_EXECUTION]: The instructions explicitly forbid the agent from executing any commands or scripts in any form, providing a safeguard against unauthorized system operations.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection as it reads content from external files (zh-CN.md) that could contain malicious instructions.
  • Ingestion points: skills/bro-mode/locales/zh-CN.md, skills/lover-mode/locales/zh-CN.md, and README.zh-CN.md (via SKILL.md instructions).
  • Boundary markers: None specified in the instructions.
  • Capability inventory: Reading and writing markdown files (restricted to .md files in the same directories).
  • Sanitization: No explicit content validation or sanitization is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 03:41 PM
Security Audit — agent-trust-hub — translate-readme-and-skills