The Agent Skills Directory

[Prompt Injection] (SAFE): The instructions are strictly limited to software design methodology. No attempts to bypass safety filters or override core agent behavior were found.- [Data Exposure & Exfiltration] (SAFE): There are no network calls, hardcoded credentials, or access to sensitive file paths. The skill only handles design templates.- [Obfuscation] (SAFE): The content is presented in clear, readable markdown. No Base64, homoglyphs, or hidden characters are present.- [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill explicitly states a 'No implementation' constraint. It does not download, install, or execute any external scripts or packages.- [Indirect Prompt Injection] (LOW): The skill is designed to ingest research documents from a prior phase. While this represents a data ingestion surface, the skill lacks any dangerous capabilities (such as shell access, file-writing, or network requests) that could be exploited through malicious input.- [Persistence Mechanisms] (SAFE): No commands for scheduled tasks, startup scripts, or system configuration changes are present.

disciplined-design