prose-style

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes local Deno scripts (prose-check.ts and rhythm.ts) to analyze text patterns. These scripts are restricted to read-only file access (--allow-read) and do not perform network operations or execute arbitrary code.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided prose text. While it reads external content, its functionality is limited to producing statistical reports and stylistic feedback, which does not present a mechanism for command injection or agent subversion.
  • [DATA_EXPOSURE]: The provided scripts read local files specified by the user to perform analysis. Access is limited to the files targeted by the user/agent and the scripts do not exfiltrate data or access sensitive system paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 11:09 AM