write
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill does not contain any malicious instructions, obfuscation, or unauthorized access patterns. Its behavior is consistent with its stated purpose of novel writing.- [DATA_EXPOSURE]: The skill reads from and writes to the local filesystem (specifically
chapters/and.sumeru/write/) to manage chapter content and track writing progress. This is a transparent and expected operation for a content creation tool.- [COMMAND_EXECUTION]: The skill describes an internal orchestration logic involving 'sub-agents' for batch chapter generation. This appears to be a descriptive workflow for the platform's execution environment rather than an attempt to execute arbitrary shell commands or external scripts.- [PROMPT_INJECTION]: No patterns of prompt injection, such as instructions to ignore safety filters or override system constraints, were identified in the instructional text.
Audit Metadata