typst-author

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a well-structured set of instructions and documentation for Typst authorship.
  • [COMMAND_EXECUTION]: The skill instructs the agent to use typst compile, typstyle, and typst eval. These are standard tools within the Typst ecosystem for document processing and syntax validation, used here for their intended purposes.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied .typ files. Typst's execution environment is sandboxed by design (limiting file system and network access), and the instructions emphasize using local documentation to verify syntax, which reduces the risk of malicious input influencing the agent's behavior through hallucinations.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 02:38 PM