research-refine
Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative Gemini review. Use when the user says "refine my approach", "帮我细化方案", "decompose this problem", "打磨idea", "refine research plan", "细化研究方案", or wants a concrete research method that stays simple, focused, and top-venue ready instead of a vague or overbuilt idea.
69
86%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Security
2 findings: 1 critical severity, 1 high severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E006: Malicious code pattern detected in skill scripts.
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
The skill contains deliberate instructions to persist and capture reviewer interactions (jobIds, threadIds, full raw responses) and to write large files silently without user permission, which enables stealthy data capture and potential exfiltration via the MCP bridge.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill repeatedly requires copying the user's "Problem Anchor" verbatim into every output and saving "FULL raw response" verbatim (including jobId/threadId and raw reviewer responses), so any secret-like text provided by the user or returned by the MCP would be echoed and persisted by the agent, creating an exfiltration risk.
Low
Low-risk findings.
1 low severity finding. 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
SKILL.md instructs the agent to “Scan grounding papers” and “search recent top-venue/arXiv work online” (runtime web/paper text), which would be ingested into the LLM context as readable prose for Phase 1.
- Commit
f4f20f9
- 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.