Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPU, collects initial results. Use when user says "实现实验", "implement experiments", "bridge", "从计划到跑实验", "deploy the plan", or has an experiment plan ready to execute.
90%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Critical
Do not install without reviewing
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.
The skill is a legitimate experiment workflow, but its Codex review prompt (lines 157-170) tells the reviewer to treat security and trust-boundary concerns as out of scope, which weakens a protection on the user's machine beyond what the research task needs, without showing malicious intent.
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.
The only outsider-authored text is an arbitrary user-configured GitHub repo (BASE_REPO) that the agent clones and reads (README, code structure) at runtime, which is a selected URL the agent must actively fetch, so it is low rather than medium.
ca70fe2
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.