The Agent Skills Directory

[SAFE]: The skill consists of documentation and tool schemas for database management. No malicious patterns, obfuscation, or unauthorized access attempts were found in the instructions or metadata.
[EXTERNAL_DOWNLOADS]: The skill fetches supplemental documentation from the official GitHub repository of the author (popup-studio-ai). These references are used for live technical guidance and are recognized as legitimate vendor resources.
[PROMPT_INJECTION]: The skill includes an indirect prompt injection surface because it retrieves and processes data from external database records (e.g., via backend_data_list).
Ingestion points: External data enters the agent context from bkend.ai database tables via CRUD tools.
Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the documentation.
Capability inventory: The skill environment permits Bash, Write, and Edit tools as defined in the allowed-tools configuration.
Sanitization: No specific sanitization or validation logic for ingested data is described. This surface is inherent to the skill's purpose as a database management assistant and is considered safe in this context.

bkend-data