novel-to-shortdrama-script
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a creative tool for scriptwriting that does not interact with the host system, network, or external APIs. It performs purely text-based transformations based on user-provided stories.
- [PROMPT_INJECTION]: The skill processes untrusted novel text as its primary input (
小说原文inSKILL.md). While the instructions do not define explicit boundary markers or sanitization logic to separate this untrusted content from the agent's core instructions, the risk is negligible. The agent has no access to actionable tools (such as shell, network, or file writing), meaning any potential injection cannot escalate beyond text generation. - [DATA_EXFILTRATION]: No data exposure or exfiltration risks were identified. The skill does not contain network-enabled tools (e.g., curl, wget) or commands that access sensitive files or environment variables.
- [REMOTE_CODE_EXECUTION]: There are no patterns suggesting remote code execution. The skill does not download or execute external scripts, and no software packages are requested in the configuration.
Audit Metadata