skills/scandit/skills/id-capture-ios/Gen Agent Trust Hub

id-capture-ios

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, vulnerabilities, or suspicious behaviors were detected in the skill instructions or provided source code.
  • [PROMPT_INJECTION]: The skill uses constraints to prevent the model from hallucinating outdated or cross-platform APIs (e.g., 'Forbidden APIs' and 'Do Not Trust Internal Knowledge' blocks). These are high-quality instructional guardrails, not malicious injections. The static detector flag regarding concealment is a false positive; it refers to the product's legitimate data anonymization features for privacy law compliance.
  • [EXTERNAL_DOWNLOADS]: All external references point to official Scandit documentation (docs.scandit.com) and their public GitHub repository for the Swift Package Manager (github.com/Scandit/datacapture-spm), which are standard and safe for this integration.
  • [CREDENTIALS_UNSAFE]: Code examples correctly use descriptive placeholders like '-- ENTER YOUR SCANDIT LICENSE KEY HERE --' instead of hardcoded secrets.
  • [DATA_EXFILTRATION]: While the skill handles sensitive identity document data (scanning passports/DLs), the example code only displays results in local UI components (alerts) and does not contain any logic to transmit this data to unauthorized third-party servers.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 03:17 AM
Security Audit — agent-trust-hub — id-capture-ios