The Agent Skills Directory

[SAFE]: The skill is entirely instructional and provides technical standards for the City of Amsterdam development teams. No security issues were detected.
[PROMPT_INJECTION]: No malicious prompt injection patterns were found. The instructions use standard directive language to guide the agent's behavior within the scope of engineering decisions (e.g., "MANDATORY: ALL architecture... decisions MUST follow these standards").
[DATA_EXFILTRATION]: No sensitive data exposure or exfiltration patterns were detected. Code examples use placeholders for sensitive fields (e.g., {tenant}, api://your-api-identifier). All network domains referenced (e.g., amsterdam.nl, github.com/Amsterdam, microsoftonline.com) are either official City of Amsterdam domains or well-known services.
[OBFUSCATION]: No obfuscated content, such as Base64, zero-width characters, or homoglyphs, was found in the skill or its reference files.
[REMOTE_CODE_EXECUTION]: The skill does not perform or instruct the agent to perform remote script execution or downloads from untrusted sources. All mentioned software packages and repositories are standard and originate from trusted domains.
[DYNAMIC_CONTEXT_INJECTION]: No usage of dynamic context injection (!command) was found in the SKILL.md file.

developers-amsterdam