qa-only
Report-only QA testing. (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 includes explicit instructions to embed a non-visible marker in AUQ text ("<gstack-qid:...>" that "doesn't render visibly") and other model-level directives (D-numbering) that are hidden/deceptive manipulations of the agent's output outside the QA-only reporting 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 `SKILL.md` the `/qa-only` runtime workflow uses the user-provided “Target URL”/scope/auth inputs to drive `$B goto/snapshot/links/console/click/fill` browser actions, which ingests and reasons over free-text/DOM content returned by that URL at runtime (outsider-authored content from pages the user points it at).
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 downloads and executes a remote installer script at runtime via curl -fsSL "https://bun.sh/install" and then runs it with bash, which is remote code execution during setup — URL flagged: https://bun.sh/install
- Repository
- garrytan/gstack
- Path
qa-only/SKILL.md
- 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.