The Agent Skills Directory

[COMMAND_EXECUTION]: The scripts/setup.py utility uses subprocess.run to automate the registration of the Dokploy MCP server with the Claude CLI. It also includes an optional flag to bypass TLS certificate validation when connecting to Dokploy instances using self-signed certificates.
[EXTERNAL_DOWNLOADS]: The skill documentation and setup scripts facilitate the download of the @sattva/dokploy-mcp package from the NPM registry using npx to establish the MCP server environment.
[REMOTE_CODE_EXECUTION]: The skill executes the Dokploy MCP server code retrieved from the external NPM registry to provide its core management capabilities.
[INDIRECT_PROMPT_INJECTION]: The skill exposes an attack surface for indirect prompt injection by allowing the agent to ingest and process log data from external applications and deployment processes.
Ingestion points: Log retrieval is performed via the application_readLogs and deployment_readLogs tools as described in references/MCP-TOOLS.md.
Boundary markers: The skill instructions do not define specific delimiters or security prompts to isolate log content from other agent instructions.
Capability inventory: The skill is configured with access to Bash, Write, and WebFetch tools.
Sanitization: No automatic filtering or sanitization of ingested log content is implemented.

dokploy-api-mcp