manuscript-optimizer

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill contains logic and guidelines for reviewing and optimizing academic manuscripts across five levels: top-level design, logic architecture, data visualization, terminology, and micro-level polish. No security risks were identified.
  • [NO_CODE]: The skill consists entirely of Markdown-based instructions for the LLM and does not include any scripts, dependencies, or external binary components.
  • [PROMPT_INJECTION]: No attempts to bypass safety filters or override system-level instructions were found. The 'Guardrails' and 'Rules' sections are strictly related to the quality and consistency of manuscript editing.
  • [DATA_EXFILTRATION]: The skill does not contain any commands or functions to access local files, environment variables, or perform network requests.
  • [REMOTE_CODE_EXECUTION]: There are no patterns involving the download or execution of remote scripts or packages.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 09:08 AM