The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses standard shell commands for project environment detection and diagnostics.
Evidence: In SKILL.md, it utilizes test, grep, sed, find, and xargs to verify the presence of configuration files (e.g., package.json, nest-cli.json), extract framework versions, and analyze module structures.
[COMMAND_EXECUTION]: The skill instructs the agent to run project-defined scripts for building and testing.
Evidence: The 'Fix Validation' section uses npm run build, npm run test, and npm run test:e2e to verify architectural integrity and business logic.
[PROMPT_INJECTION] (Indirect): The skill possesses an attack surface for indirect prompt injection as it ingests untrusted data from the local filesystem.
Evidence:
Ingestion points: Reads package.json, nest-cli.json, tsconfig.json, and various .ts files under the src/ directory.
Boundary markers: Absent. There are no explicit delimiters or instructions to ignore malicious content within the analyzed files.
Capability inventory: The skill can execute shell commands (find, grep) and invoke build/test scripts via npm.
Sanitization: No sanitization or validation of the ingested file content is performed before the agent processes it.

nestjs-expert