design-consultation
Design consultation: understands your product, researches the landscape, proposes a complete design system (aesthetic, typography, color, layout, spacing, motion), and generates font+color preview... (gstack)
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 explicitly instructs the agent to embed a hidden/invisible marker (<gstack-qid:...> wrapped in angle brackets) into AskUserQuestion text so hooks can parse it, which is a concealed instruction that modifies agent output/behavior outside the stated design-consultation 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
[Excludes.] The required runtime workflow for `/design-consultation` ingests only trusted first-party/local content (repo files like `README.md`, `package.json`, `src/...`, existing `DESIGN.md`/local office-hours artifacts, and locally stored taste/learning JSON), plus the user’s own chat responses, and it does not include reading arbitrary outsider-authored free text by default (external research is conditional on user saying yes and still relies on the agent’s explicit search/fetch behavior, which is categorized as low rather than medium.)
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 executes a remote installer script at runtime via curl -fsSL "https://bun.sh/install" and then runs it with bash, which is fetching and executing remote code.
- 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.