The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to read target project files and write integration code directly into them. This workflow creates a surface for indirect prompt injection if the files being processed contain malicious instructions designed to influence the agent's behavior during the integration process.
Ingestion points: User-specified Flutter project files (e.g., BLoC, controller, or widget files) as described in references/integration.md and references/migration.md.
Boundary markers: The skill does not provide specific delimiters or instructions to ignore embedded commands within the files being processed.
Capability inventory: The agent is authorized to perform file-read and file-write operations on the user's local codebase to apply code snippets.
Sanitization: No specific validation or sanitization steps are defined for the content read from or written to the project files.
[EXTERNAL_DOWNLOADS]: The skill references documentation, samples, and account management pages from Scandit's official domains and GitHub repositories. These are documented as standard functional references for a vendor-authored skill.
Evidence: Links to docs.scandit.com, ssl.scandit.com, and github.com/Scandit in SKILL.md and references/integration.md.

matrixscan-ar-flutter