The Agent Skills Directory

[SAFE]: The skill consists entirely of development documentation, directory structures, and code templates. No malicious behavior or security risks were identified.- [COMMAND_EXECUTION]: The skill documents standard development commands such as make, uv run pytest, and alembic revision. These are typical for the described software development workflow and do not pose a security risk in this context.- [DATA_EXFILTRATION]: No hardcoded credentials, sensitive file access, or unauthorized network operations were found. The code patterns for database access and GraphQL resolvers follow standard practices, including the use of permission classes.- [PROMPT_INJECTION]: The instructions are focused on guiding the agent through backend tasks. There are no attempts to override system prompts or bypass safety guidelines.- [EXTERNAL_DOWNLOADS]: The skill mentions using standard development tools like uv and pytest but does not contain instructions for downloading or executing scripts from untrusted remote sources.

phoenix-server