swift-formatstyle

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill consists entirely of instructional Markdown and code snippets. It contains no executable scripts, shell commands, or binary files.\n- [SAFE]: No network operations, credential exposures, or remote dependency installations were detected. Documentation links provided are purely for reference and do not involve code downloads.\n- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing untrusted data (numbers, dates, URLs) via formatting APIs.\n
  • Ingestion points: SKILL.md and references/formatstyle-recipes.md describe formatting various user-provided types.\n
  • Boundary markers: None explicitly defined in the provided snippets.\n
  • Capability inventory: No subprocess execution, file system modifications, or network transmissions are documented; operations are limited to system library formatting calls.\n
  • Sanitization: The skill includes explicit warnings that formatting is for display and should not be treated as a security or sanitization boundary, demonstrating security awareness in its design.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 03:43 PM