The Agent Skills Directory

[Command Execution] (SAFE): The skill utilizes legitimate commands (nx generate, nx affected, npx prettier) for monorepo management. These are restricted to the intended purpose of code generation and formatting.
[Prompt Injection] (SAFE): No evidence of instruction override, safety filter bypass, or role-play injection. The instructional content is focused and benign.
[Data Exposure & Exfiltration] (SAFE): The skill does not access sensitive directories (~/.ssh, ~/.aws) or hardcode any credentials. No unauthorized network exfiltration patterns were identified.
[Indirect Prompt Injection] (SAFE): While the skill interacts with generator schemas via mcp__nx-mcp__nx_generator_schema, this is the primary intended function. The risk of processing malicious schemas is mitigated by the scope of the nx CLI.
Ingestion points: Generator schemas processed by mcp tools.
Boundary markers: Implicitly handled by the Nx CLI parameter structure.
Capability inventory: Bash tool execution of local generators.
Sanitization: Relies on Nx's internal schema validation.

run-nx-generator