Use when preparing an app for translation, checking localization infrastructure, or when pseudo-localization comes up. Replaces strings with accented, 35%-longer variants to expose hardcoded text, truncation, encoding and bidi problems without real translators.
90%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
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 runs pseudo-localization tools on the team's own source locale files and scans the rendered pages of the team's own app via Playwright, so outsider text reaches the agent only if the app displays user-generated content on a page the agent is directed to visit, which makes this a low-risk on-demand fetch rather than a monitored queue.