swift-charts

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEMETADATA_POISONINGINDIRECT_PROMPT_INJECTION
Full Analysis
  • [METADATA_POISONING]: The skill contains deceptive information regarding its technical scope and resources.
  • Evidence: Claims to target 'iOS 26+' (a fictional version) throughout the documentation (e.g., in SKILL.md and multiple reference files).
  • Evidence: Provides Apple documentation links using the 'sosumi.ai' domain instead of the official 'developer.apple.com' domain.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines patterns for processing external data into UI components, which is a standard injection surface.
  • Ingestion points: Data is ingested through the Chart(data) and BarPlot(largeDataset, ...) initializers in SKILL.md and the reference files.
  • Boundary markers: The instructions do not define delimiters or specific 'ignore instructions' warnings for the data being charted.
  • Capability inventory: The skill utilizes SwiftUI chart rendering capabilities; no evidence of shell execution or file-system writing was found.
  • Sanitization: There is no guidance provided for sanitizing or validating the contents of the data before it is rendered into chart marks or labels.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 11:14 AM
Security Audit — agent-trust-hub — swift-charts