Skills
Navigate
skills/scandit/skills/id-capture-capacitor/Gen Agent Trust Hub

id-capture-capacitor

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the capture and processing of data from physical identity documents (MRZ, VIZ, barcodes, and mobile documents). This data constitutes untrusted external input that is ingested into the agent context. However, the skill explicitly provides safety guidance to avoid logging personal data and highlights built-in anonymization modes to mitigate privacy risks.
  • Ingestion points: Identified in references/integration.md and references/supplementary-modules.md via the IdCapture and CapturedId APIs.
  • Boundary markers: Not explicitly defined for the captured data strings.
  • Capability inventory: The instructions guide the creation of applications with camera access, file system access (indirectly via Capacitor), and network capabilities.
  • Sanitization: Includes instructions for IdAnonymizationMode and per-field anonymization in references/integration.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 10:57 PM