The Agent Skills Directory

[PROMPT_INJECTION]: The skill analyzes external data including IaC files, configurations, and workflows to perform Swiss FADP gap assessments, creating a surface for indirect prompt injection if those files contain malicious instructions.
Ingestion points: The skill utilizes Read, Glob, and Grep tools to retrieve content from the local project environment as described in its usage examples.
Boundary markers: The instructions do not define explicit delimiters or instructions for the agent to ignore commands that may be embedded within analyzed files.
Capability inventory: The skill possesses the Write tool, allowing it to modify files or generate remediation code based on its analysis of external data.
Sanitization: No explicit logic for content sanitization or validation is specified for the files processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill references official and well-known external resources for legal text and framework mappings.
Evidence: Links to the official Swiss Federal Data Protection and Information Commissioner (edoeb.admin.ch) and the Federal Chancellery (fedlex.admin.ch) for authoritative legal text.
Evidence: Integrates with the Secure Controls Framework (securecontrolsframework.com) to provide standardized regulatory mappings.

ch-fadp-expert