swift-charts

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [METADATA_POISONING]: The skill documentation refers to non-existent platform versions (e.g., iOS 26), which can mislead the agent about available APIs and system capabilities.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data for chart labels and annotations without providing instructions for sanitization or boundary enforcement.
  • Ingestion points: Data collections such as 'spend' in SKILL.md and 'points' in references/interaction.md.
  • Boundary markers: None specified for data-driven text.
  • Capability inventory: Uses AxisValueLabel and .annotation to render user-provided data.
  • Sanitization: No mention of string escaping or validation for plottable values.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 09:01 PM
Security Audit — agent-trust-hub — swift-charts