The Agent Skills Directory

[DATA_EXFILTRATION]: The skill communicates exclusively with the official vendor API at https://api.studiochat.io. Authentication is managed through environment variables (STUDIO_API_TOKEN), ensuring that credentials are not hardcoded or exposed in command history. No unauthorized data exfiltration or access to sensitive local files was detected.- [PROMPT_INJECTION]: The instructions include a safety-focused operational guardrail, requiring the agent to obtain explicit user confirmation before performing any create, update, or delete operations. The skill manages instructional content (Playbooks and Skills), which is a standard administrative function and does not contain malicious injection patterns.- [COMMAND_EXECUTION]: All API interactions are handled by a provided Python script (scripts/api.py). The script uses the standard Python urllib library for structured HTTP requests and does not perform arbitrary shell command execution or system-level modifications.- [SAFE]: The skill's behavior is consistent with its stated purpose of configuring assistant settings, knowledge bases, and tools. All external resources, including the API domain and script logic, belong to the vendor, studiochat.

builder