design-review
Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. (gstack)
Security
3 findings — 1 critical severity, 2 medium severity. 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
Potential prompt injection detected (high risk: 0.70). The skill explicitly instructs the agent to embed an invisible marker (<gstack-qid:...>) into rendered AskUserQuestion text that "doesn't render visibly to the user" — a hidden/deceptive instruction (even if for telemetry/auto-decision) that alters output invisibly and thus qualifies as prompt-injection risk.
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
Third-party content exposure detected (medium risk: 0.65). Runtime path: the skill uses `$B goto <target URL>` and then extracts rendered page content via browser automation (screenshots + DOM-evaluated data like fonts/colors/text), so any free-form text on an outsider-controlled web page (or user-supplied URL) can be ingested into the agent’s LLM context as readable prose/DOM-derived strings.
W012: Unverifiable external dependency detected (runtime URL that controls agent)
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
Potentially malicious external URL detected (high risk: 0.80). The skill's setup step conditionally downloads and executes the Bun install script from https://bun.sh/install (curl -fsSL "https://bun.sh/install" -o "$tmpfile" ... && BUN_VERSION="$BUN_VERSION" bash "$tmpfile"), so a remote URL is fetched and executed at runtime.
- Repository
- garrytan/gstack
- Commit
a325940
- 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.