devex-review
Live developer experience audit. (gstack)
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 skill’s required runtime workflow explicitly uses the browse tool to “navigate docs” and test web-accessible surfaces (including community pages like “GitHub issues”), which means it will ingest outsider-authored free text from those pages at runtime when searching/clicking through the user/product-provided URLs.
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 conditionally runs `curl -fsSL "https://bun.sh/install" -o "$tmpfile"` and then executes that downloaded script with `bash "$tmpfile"`, which fetches and runs remote code at runtime (https://bun.sh/install).
- 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.