Write and run scoped Playwright browser automation, responsive checks, screenshots and login-flow tests with a local Node executor.
69%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Critical
Do not install without reviewing
Fix and improve this skill with Tessl
tessl review fix ./plugins/aasb-aas-accessibility-inclusive-ux/skills/playwright-skill/SKILL.mdDetected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
The skill is a documented Playwright automation toolkit with disclosed code execution and header behavior, but its example link checker sends HEAD requests to every external link on a page, which could reach off-scope destinations in an authenticated context, a sketchy behavior the user would not expect (no malicious intent is shown).
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow navigates a browser to a user-specified or auto-detected URL and reads page content (title, DOM, table text, links), which is outsider-authored web content the agent must actively select and fetch, so this is low exposure rather than a monitored queue.
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.