mystery-novel-conventions
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Prompt Injection] (SAFE): The content consists entirely of writing advice. No override patterns, jailbreak attempts, or system prompt extraction instructions were found.- [Data Exposure & Exfiltration] (SAFE): No sensitive file paths (e.g., .ssh, .aws) are mentioned, and there are no network operations (curl, wget) to external domains.- [Obfuscation] (SAFE): No Base64, zero-width characters, or homoglyphs were detected. The text is plain markdown.- [Unverifiable Dependencies & RCE] (SAFE): No package managers (pip, npm) or remote script executions are present in the skill files.- [Command Execution] (SAFE): The skill only uses 'Read' and 'Grep' tools for its intended purpose and does not execute any shell commands or subprocesses.
Audit Metadata