The Agent Skills Directory

[SAFE]: The skill explicitly forbids the use of hardcoded credentials, tokens, or URLs in test scripts, promoting the use of environment variables (process.env) as a secure alternative.
[SAFE]: All identified tools and dependencies, such as Playwright and Appium, are reputable and industry-standard for the stated purpose of the skill.
[PROMPT_INJECTION]: The skill processes untrusted external test design files, creating an indirect prompt injection surface. This risk is minimized by the skill's rigid template-based code generation approach.
Ingestion points: Zephyr test design files (per SKILL.md description).
Boundary markers: Absent; the skill does not define specific separators for the input data.
Capability inventory: Performs file system writes to create .ts files in src/test/ and src/page/ directories.
Sanitization: Absent; the agent is instructed to translate design content directly into implementation code.

implementer-agent