aris-experiment-bridge
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.
71
88%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
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 explicitly instructs the agent to "paste the experiment scripts" into a cross-model review prompt (mcp__codex__codex), which would cause the LLM to transmit any embedded secrets (API keys, tokens, creds) verbatim to another model — enabling secret exfiltration.
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
Experiment Bridge reads outsider-authored free text from plan files such as `refine-logs/EXPERIMENT_PLAN.md` (and `FINAL_PROPOSAL.md`/`IDEA_REPORT.md`) at runtime in Phase 1/2, enabling prompt injection via user-provided experiment plans and related documents.
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 explicitly clones a user-provided BASE_REPO at runtime ("git clone <BASE_REPO>") and the override gives the URL https://github.com/org/project, so remote repository code would be fetched and could be executed as part of the workflow.
- Repository
- OpenLAIR/dr-claw
- Commit
6da7f7c
- 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.