book-revision-coach
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected in the skill's instructions or workflow.
- [PROMPT_INJECTION]: The instructions are focused on textual analysis and editing guidelines. No attempts to bypass safety filters, extract system prompts, or override agent behavior were found.
- [DATA_EXFILTRATION]: The skill does not access sensitive local file paths (such as .ssh, .aws, or .env) nor does it perform network operations to exfiltrate user data. References to external URLs are for documentation and regulatory standards only.
- [REMOTE_CODE_EXECUTION]: There are no commands for downloading and executing scripts, installing unverified packages, or performing runtime code compilation.
- [EXTERNAL_DOWNLOADS]: External links point to official South Korean government and industry organizations, such as the National Institute of Korean Language (korean.go.kr) and the Korea Copyright Commission (copyright.or.kr), which are trusted sources for linguistic and legal guidelines.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided manuscript drafts. While it ingests external content, its capabilities are limited to providing analysis and reports, lacking the high-privilege tools (like shell execution or network writing) required to exploit injection vulnerabilities.
Audit Metadata