The Agent Skills Directory

[SAFE]: The skill provides structured templates and instructions for performing production smoke tests and SEO audits using industry-standard tools like Playwright.
[SAFE]: Credential management guidelines explicitly discourage hardcoding secrets, instead recommending the use of environment variables and dedicated smoke-test accounts.
[SAFE]: Network operations performed via the included Bash and Playwright scripts are limited to fetching web content for the purpose of link validation and response code checking, which aligns with the skill's primary function.
[SAFE]: The skill exhibits an inherent attack surface for indirect prompt injection because it is designed to ingest and process data from live websites. This risk is minimized by the skill's specific focus on structured validation (status codes, tag counts) rather than open-ended natural language processing of untrusted page content.
Ingestion points: validate-redirects.sh (line 74), smoke-test.spec.ts (line 52).
Boundary markers: None present in the provided templates.
Capability inventory: Use of Bash(*), Write, and Edit tools.
Sanitization: The scripts perform automated checks on specific attributes (like status codes and tag presence) rather than passing raw page text into an LLM prompt.

qa-automation-specialist