open-gstack-browser
Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
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.
Why it was flagged
The required workflow launches a browser and runs a demo against Hacker News (news.ycombinator.com), but navigating to external web pages during a demo or browse session constitutes actively fetching selected/searchable URLs rather than monitoring an automatic queue.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The script fetches Bun from `https://bun.sh/install` under weak/unknown provenance conditions to install an external runtime tool, making it an unverifiable operational dependency.
- Repository
- garrytan/gstack
- Commit
96764e8
- Audited
- Security analysis
Is this your skill?
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.