Post-deploy canary monitoring. (gstack)
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 skill monitors arbitrary user-provided web URLs by driving a browser and ingesting rendered page content and text snapshots.
garrytan/gstack
canary/SKILL.md
f0cd9f8
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.