novel-evaluator
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Prompt Injection (SAFE): No malicious instructions or bypass attempts were found in the skill's prompts. The instructions focus strictly on story evaluation.
- Data Exposure & Exfiltration (SAFE): The skill does not access sensitive files or perform network operations. It only uses the 'Read' tool to process story content.
- Indirect Prompt Injection (SAFE): Although the skill processes untrusted story manuscripts, it lacks dangerous tools (like shell access or network writing) that could be exploited via injection. The instructions specifically mandate evaluation based on content rather than instruction following.
Audit Metadata