The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses the npx command to download and execute the @claude-flow/cli package from the npm registry. Because it uses the @latest tag, it pulls unpinned remote code every time the storage or hook steps are executed.
[REMOTE_CODE_EXECUTION]: By invoking npx @claude-flow/cli@latest, the skill performs remote code execution at runtime, running code that is not contained within the skill's source files.
[COMMAND_EXECUTION]: The skill utilizes Bash to perform file system discovery via find, text pattern matching with grep, and the execution of the external CLI utility.
[PROMPT_INJECTION]:
Ingestion points: The skill reads local TypeScript (.ts) source code files to detect architectural violations.
Boundary markers: There are no explicit boundary markers or instructions to ignore instructions embedded within the analyzed source code files.
Capability inventory: The agent has access to Bash (including npx and grep), file read operations, and persistent memory storage tools.
Sanitization: The skill does not define sanitization or escaping procedures for the source code content before it is formatted into the final summary report or stored in memory.

ddd-validate