fiction-workshop
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use
npx hwpxjs txtto facilitate the extraction of text from HWPX files for the version comparison feature. - [DYNAMIC_EXECUTION]: The instructions suggest automating quantitative analysis, such as calculating sentence length distributions and pattern frequencies, through the use of scripts at runtime.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user-provided manuscripts and literary works.
- Ingestion points: Literary works, short stories, and multiple versions of manuscripts provided by the user for revision.
- Boundary markers: None identified in the provided instructions.
- Capability inventory: Execution of shell commands via
npx, generation of HWPX output files, and execution of analysis scripts. - Sanitization: The skill does not explicitly describe sanitization or escaping of the input text before processing.
Audit Metadata