The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional Markdown content and reference guides. No executable scripts or configuration files that could be used for malicious purposes are included.
[SAFE]: No external dependencies, remote code execution patterns, or network exfiltration attempts were detected. All URL references are for documentation purposes (e.g., example.com).
[SAFE]: The skill promotes security best practices by including a specific 'Security Review' phase that instructs the agent to check for SQL injection, proper authentication (OAuth 2.0, JWT), and secrets management using dedicated managers rather than hardcoded credentials.
[INDIRECT_PROMPT_INJECTION]: The skill's primary purpose involves ingesting external design documentation provided by the user (architecture diagrams, API specs). While this creates an ingestion point for potentially untrusted data, the skill does not possess sensitive capabilities like file-writing or arbitrary command execution that would allow for an exploit chain. As this ingestion is central to the skill's intended function, it is considered acceptable.

backend-design-review