The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides numerous curl commands to interact with the Base44 API and MCP endpoints. These commands perform resource management tasks such as creating apps, querying tool schemas, and listing configurations. It also references a troubleshooting utility, zero, used for verifying connector health.
[EXTERNAL_DOWNLOADS]: The skill performs legitimate network requests to app.base44.com as part of its primary integration purpose. This includes an operation to download application source code archives to the local /tmp directory.
[DATA_EXFILTRATION]: Sensitive operations are authenticated using the BASE44_TOKEN environment variable, which is passed in the Authorization header of HTTP requests. These requests are restricted to the service's official domain (app.base44.com), and no unexpected data transmission to third-party domains was observed.
[PROMPT_INJECTION]: The skill acts as an interface for external data retrieved from the Base44 service, which could theoretically be used for indirect prompt injection if the service's responses were manipulated.
Ingestion points: API responses from https://app.base44.com/api/apps and tool definitions from the MCP endpoint at https://app.base44.com/mcp as described in SKILL.md.
Boundary markers: The skill does not employ specific delimiters or warnings to isolate external API data from the agent's core instructions.
Capability inventory: The skill utilizes network communication (curl) and file system writes (writing to /tmp/).
Sanitization: Responses are processed using jq for structural parsing, but there is no explicit sanitization of natural language content contained within the API results.

base44