The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill utilizes npx in the scripts/scan.sh script to dynamically download and execute well-known packages including eslint, eslint-plugin-playwright, eslint-plugin-cypress, and @ast-grep/cli from the official npm registry. These downloads are from a trusted/well-known service and are necessary for the skill's primary function.
[COMMAND_EXECUTION]: The skill executes a bundled shell script (scripts/scan.sh) to perform mechanical scans of the user's test directory. This script invokes standard CLI utilities such as ripgrep and ast-grep to process files and detect code patterns.
[PROMPT_INJECTION]: The skill processes untrusted content from the user's test files, which constitutes a surface for indirect prompt injection (Category 8). However, this is inherent to the skill's purpose as an E2E test auditor.
Ingestion points: Spec files (.spec.ts, .cy.js) and Page Object Model (POM) files within the project directory being analyzed.
Boundary markers: Absent. The skill does not instruct the agent to use specific delimiters to separate untrusted code from its operational instructions.
Capability inventory: Execution of analysis scripts (scripts/scan.sh), file system reading, and execution of linting tools.
Sanitization: No evidence of content sanitization or filtering is present; the skill analyzes the provided code as-is.

e2e-reviewer