story-setup
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPRIVILEGE_ESCALATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-generated novel text and has file-write permissions. While it lacks explicit instruction delimiters, the sub-agents are strictly defined with specialized instructions to minimize exploitation risks.
- [EXTERNAL_DOWNLOADS]: A maintenance script queries the author's GitHub repository to check for updates. This is a common, non-malicious behavior using a well-known service.
- [COMMAND_EXECUTION]: Local scripts utilize Git commands and Node.js to manage project infrastructure and execute validation tasks. These commands are necessary for the skill's deployment and monitoring functions.
- [PRIVILEGE_ESCALATION]: The skill applies execute permissions to its own deployed hook scripts. This is part of the standard setup process for local Git hooks and does not involve unauthorized privilege gains.
Audit Metadata