p-pdf-preview

Pass

Audited by Gen Agent Trust Hub on Jun 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill automates the creation of a standard directory structure using common shell utilities such as mkdir, cat, and printf. These operations are well-scoped to a local literatures directory and represent standard administrative behavior for an agent.
  • [SAFE]: The skill processes user-provided inputs (such as paper titles and themes) to generate directory names. To mitigate the risk of indirect injection or filesystem errors, the instructions provide a comprehensive list of illegal characters to be removed from user-supplied strings, demonstrating a secure-by-design approach to handling untrusted data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 30, 2026, 08:13 AM