The Agent Skills Directory

[SAFE]: The skill is a well-structured set of instructions and references for the NocoBase data modeling environment. No malicious patterns, prompt injections, or obfuscated content were detected across the analyzed files.- [DATA_EXPOSURE_AND_EXFILTRATION]: There are no hardcoded credentials, API keys, or attempts to access sensitive system files like SSH keys or environment variables. The instructions explicitly direct the agent to handle authentication errors by guiding the user to authenticate through standard vendor channels.- [REMOTE_CODE_EXECUTION]: The skill does not perform unauthorized remote code execution or download scripts from unknown sources. It relies on a local vendor-provided CLI tool (nocobase-ctl) for its operations. No suspicious package installations (npm/pip) were found.- [PROMPT_INJECTION]: The skill uses natural instructional language and established modeling rules without attempting to bypass safety filters, extract system prompts, or override agent constraints.- [COMMAND_EXECUTION]: Shell access is scoped to the nocobase-ctl CLI for inspecting and updating collection schemas. The skill includes mandatory gates to ensure commands are run with help flags and proper context.- [OBFUSCATION]: All instructions and JSON examples are provided in clear text. There is no evidence of Base64 encoding, zero-width characters, or other techniques used to hide malicious intent.

nocobase-data-modeling