experiment-bridge
What this skill does
The skill 'experiment-bridge' is designed to automate the implementation and deployment of experiments based on a provided plan. It is intended for use in a research or development workflow where an e
github/wanshuiyin - Potential Misuse of Deployment - 14.5k stars
Threat analysis
Skill info
pkg:github/wanshuiyin/Auto-claude-code-research-in-sleep@bab594e?skill=experiment-bridgeAssessments (2)
Potential Misuse of Deployment
Potential Misuse of Deployment via local-llm-review
SKILL.md
The skill includes the constant **AUTO_DEPLOY = true**, which automatically deploys experiments after implementation and review. If the deployment target is not properly secured or if the code is not Lack of Explicit Security Controls
Lack of Explicit Security Controls via local-llm-review
SKILL.md
The skill does not explicitly mention any security controls such as input validation, access control, or verification of the deployment environment. This could lead to potential misuse if the skill isBadge
Add the Anomity scan badge for experiment-bridge to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of experiment-bridge? Report an issue or request a rescan.
