The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes project source code and existing test files to identify missing test cases and generate new ones. This creates a surface for indirect prompt injection where malicious instructions embedded in the analyzed code could potentially influence the agent's logic.
Ingestion points: Project production code (components, services, pipes, etc.), existing *.spec.ts files, and configuration files like angular.json or jest.config.js (SKILL.md, Phase 1 & 3).
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts within the ingested code.
Capability inventory: The agent can read/write local files, execute shell commands via test runners, and dispatch sub-agents (SKILL.md, Phase 2 & 3).
Sanitization: No sanitization or validation of the input source code is performed before processing.
[COMMAND_EXECUTION]: The skill invokes shell commands to run the project's test suite, specifically using ng test, npx jest, and npx vitest (SKILL.md, Phase 2). While these are the intended functions for an Angular testing utility, they involve executing code that is influenced by the project's local configuration and the generated test files.

angular-tester