The Agent Skills Directory

[SAFE]: The skill demonstrates safe credential management practices in references/playwright-ts-patterns.md by retrieving test user credentials from process.env rather than hardcoding sensitive data.
[COMMAND_EXECUTION]: The skill is explicitly designed to execute shell commands for its primary purpose of running test suites (e.g., pytest, npx vitest, npx playwright). These operations are restricted to standard testing frameworks and are used as intended for a development-focused agent.
[PROMPT_INJECTION]: Indirect Prompt Injection analysis (Category 8):
Ingestion points: The skill reads external specification and implementation files to determine test requirements as defined in SKILL.md.
Boundary markers: None identified; the agent processes source code directly without specific delimiters to ignore embedded instructions.
Capability inventory: The skill can execute arbitrary testing commands and write test files across the repository as detailed in the various references/ files.
Sanitization: No explicit sanitization or validation of the ingested code content is performed before processing.

tester