The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions involve executing local CLI commands using npx codeceptjs for setup verification, inventory listing, and running verified test scenarios. Evidence: workflow steps 2 and 10 in SKILL.md.- [PROMPT_INJECTION]: The skill processes data from external web pages via the CodeceptJS MCP server, which presents a surface for indirect prompt injection. * Ingestion points: HTML and ARIA snapshots provided by the MCP server's run_code and run_test actions as described in steps 7 and 9 of SKILL.md. * Boundary markers: Absent; the instructions do not specify delimiters to distinguish page content from agent instructions. * Capability inventory: The skill can execute browser actions and local shell commands through the CodeceptJS actor and CLI as defined in the test authoring workflow. * Sanitization: No content sanitization or filtering is specified for the data ingested from the browser session.

writing-codeceptjs-tests