matrixscan-batch-ios
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill contains instructions for the agent to provide masked previews of license keys in the chat and when applying code to files. This is a security measure to prevent the exposure of sensitive API keys in logs or history, rather than a malicious attempt to hide actions from the user.
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes local project files to generate integration code.
- Ingestion points: Project manifests (Package.resolved, Podfile.lock) and Swift source files.
- Boundary markers: No specific delimiters are defined for processing local file content.
- Capability inventory: The agent is instructed to write code directly to the local filesystem.
- Sanitization: No explicit sanitization or validation of the ingested project data is implemented.
- [EXTERNAL_DOWNLOADS]: The skill references the Scandit Data Capture SDK for iOS, which is hosted on an official GitHub repository and managed via standard dependency managers like Swift Package Manager.
Audit Metadata