Review a flutter_rust_bridge PR before treating it as ready, including subagent checks for correctness and test weakening plus Gemini review.
75
92%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
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.
This workflow requires reviewing an external PR diff and Gemini’s external review/comments, which are outsider-authored free-text retrieved at runtime and would be ingested into the agent/LLM context (categories: PR/issues/discussion text; web/external review output).
1d5348b
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.