The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the claude-flow package from the npm registry to enable its orchestration capabilities. This is a standard dependency for the framework described by the vendor.
[COMMAND_EXECUTION]: The orchestration patterns include the use of tools such as mcp__claude-flow__parallel_execute to run development and testing commands like npm run test. These operations are consistent with the skill's primary purpose of managing software development and research workflows.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection through its ingestion of external research and analysis data.
Ingestion points: Data is collected from external sources via mcp__claude-flow__memory_usage and analyzed using tools like mcp__claude-flow__error_analysis.
Boundary markers: The patterns do not specify explicit delimiters or isolation markers for untrusted content within the agent's context.
Capability inventory: The framework has high-level capabilities, including shell command execution, CI/CD pipeline creation, and file system interactions.
Sanitization: There are no documented steps for validating or sanitizing external content before it is processed by the orchestration tools.

swarm-advanced