open-gstack-browser
Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in.
Security
1 critical severity finding. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E004: Prompt injection detected in skill instructions.
What this means
Detected 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.
Why it was flagged
The skill instructs the model to embed an invisible marker (e.g. <gstack-qid:...> wrapped in angle brackets that "doesn't render visibly") in AskUserQuestion outputs so external hooks can parse it—a hidden/deceptive instruction that influences behavior outside the skill's user-facing purpose.
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
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
In the “open gstack browser” workflow, the sidebar chat/agent in the launched Chromium can “navigate pages… and read content” based on user instructions, so outsider-authored webpage text can be ingested at runtime when the user browses arbitrary sites.
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 skill's setup step downloads and then executes a remote installer script via curl -fsSL "https://bun.sh/install" -o "$tmpfile" and then runs it with bash, so this runtime fetch executes remote code (https://bun.sh/install).
- Repository
- garrytan/gstack
- Commit
d078622
- 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.