The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill architecture relies on ingesting user requirements to generate and execute code without explicit delimiters or instructions to ignore embedded commands. This creates a surface where malicious instructions hidden in application requirements could potentially influence the agent's logic.
Ingestion points: Requirement analysis phase described in the core workflow.
Boundary markers: Not present; the instructions do not specify how to isolate user requirements from the agent's system instructions.
Capability inventory: Shell execution capabilities including npm run test, npm run lint, and nest info.
Sanitization: Absent; there is no mention of filtering or validating the requirement text for instruction-like patterns.
[EXTERNAL_DOWNLOADS]: The skill metadata and documentation links point to jeffallan.github.io. Although this is a common hosting platform, the specific domain has been flagged by automated scanners. While no direct script downloads were observed, users should exercise caution with external links.
[COMMAND_EXECUTION]: The workflow incorporates the use of project-level CLI tools (npm, nest). These commands are standard for the described task but represent a capability that interacts with the local shell environment.

nestjs-expert