design-html
Design finalization: generates production-quality Pretext-native HTML/CSS. (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 instructs the model to append an invisible marker like "<gstack-qid:{question_id}>" into AskUserQuestion text (the marker "doesn't render visibly" and is stripped by hooks), which is a hidden, non-user-visible instruction used for enforcement/auto-decide outside the primary visible behavior of the design-html skill.
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
The `/design-html` skill reads user/outsider-authored free text at runtime via the user's description and the CEO plan / design review notes files it ingests, and then passes that content into Pretext/HTML generation (e.g., Step 1 uses plan prose or user-described requirements to generate the implementation spec, and Step 4 iterates on user feedback).
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 invokes a remote installer (curl -fsSL "https://bun.sh/install" … bash) at runtime and also falls back to importing runtime JS from "https://esm.sh/@chenglou/pretext" into generated HTML, both of which fetch and execute remote code during skill execution.
- 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.