qa-only
Report-only QA testing. Systematically tests a web application and produces a structured report with health score, screenshots, and repro steps — but never fixes anything. Use when asked to "just report bugs", "qa report only", or "test but don't fix". For the full test-fix-verify loop, use /qa instead. Proactively suggest when the user wants a bug report without any code changes. (gstack) Voice triggers (speech-to-text aliases): "bug report", "just check for bugs".
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: 0.80). The skill advertises "qa-only" report-only behavior but contains numerous explicit instructions that modify project files, commit changes, change telemetry/routing/config, and run repo-altering commands (e.g., creating/committing CLAUDE.md, git rm of vendored code, setting gstack-config), which are outside the stated report-only scope and thus represent deceptive/out-of-scope instructions.
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 (high risk: 0.80). The skill explicitly instructs the agent to visit and interact with arbitrary target URLs as part of its QA workflow (e.g., "Target URL" parameter and commands like `$B goto <target-url>` in Setup/Modes/Workflow) and even fetch public resources (curl https://bun.sh/install), so untrusted third-party page content is ingested and used to drive decisions and actions.
W012: Unverifiable external dependency detected (runtime URL that controls agent)
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
Potentially malicious external URL detected (high risk: 1.00). The skill's setup step fetches and executes a remote installer script at https://bun.sh/install (curl -fsSL "https://bun.sh/install" -o "$tmpfile" then bash "$tmpfile"), which is used at runtime to install a required dependency for the browse tool—so remote content is fetched and executed.
- Repository
- garrytan/gstack
- Commit
db9447c
- 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.