Beacon Threat Intelligence
Security intelligence for the agent supply chain
Every MCP server and agent skill the public registries list, matched to its source repository, with Beacon's rating of what it can do to your agent and your machine.
| Name | Risk |
|---|---|
| compose-animations chrisbanes/skills | |
| compose-component-design chrisbanes/skills | |
| compose-focus-navigation chrisbanes/skills | |
| compose-modifier-and-layout-style chrisbanes/skills | |
| compose-performance chrisbanes/skills | |
| compose-recomposition-performance chrisbanes/skills | |
| compose-side-effects chrisbanes/skills | |
| compose-slot-api-pattern chrisbanes/skills | |
| compose-stability-diagnostics chrisbanes/skills | |
| compose-state-and-effects chrisbanes/skills | |
| compose-state-authoring chrisbanes/skills | |
| compose-state-deferred-reads chrisbanes/skills | |
| compose-state-hoisting chrisbanes/skills | |
| compose-state-holder-ui-split chrisbanes/skills | |
| compose-ui-testing-patterns chrisbanes/skills | |
| gradle-run chrisbanes/skills | |
| grounded-writing chrisbanes/skills | |
| implement-with-subagents chrisbanes/skills | |
| kotlin-api-design chrisbanes/skills | |
| kotlin-concurrency-and-flow chrisbanes/skills | |
| kotlin-control-flow chrisbanes/skills | |
| kotlin-coroutines-structured-concurrency chrisbanes/skills | |
| kotlin-flow-state-event-modeling chrisbanes/skills | |
| kotlin-multiplatform-expect-actual chrisbanes/skills | |
| kotlin-types-value-class chrisbanes/skills | |
| run-github-project chrisbanes/skills | |
| shepherd chrisbanes/skills | |
| to-plan chrisbanes/skills | |
| using-chrisbanes-skills chrisbanes/skills | |
| stream-repro chrisbenincasa/tunarr Reproduce and measure Tunarr stream bugs on an isolated server. Boots a throwaway Tunarr server, builds a channel from synthetic clips (or a copy of the dev database), captures a bounded HLS or MPEG-TS sample, and reports per-segment tracks | |
| feature-walkthrough chrisleekr/binance-trading-bot Autonomously test the running binance-trading-bot app in a real browser. The agent drives the browser itself via the Playwright MCP - logs in, looks at each screen, and works through every feature end-to-end like a real operator, finding an | |
| d3-viz chrisvoncsefalvay/claude-d3js-skill | |
| analyzing-sql-traces chromium/chromium Extracts raw trace data from Perfetto traces, runs arbitrary SQL queries for custom follow-up analysis, and applies expert cognitive principles (Tiered Flow Analysis, Semantic Mismatch, Redundancy) to identify performance bottlenecks, struc | |
| automated-tracing chromium/chromium Automated Tracing & Performance Telemetry in Chromium using Perfetto and Telemetry benchmarks. Use when you need to launch the browser binary, execute a specific scenario/story, and collect Perfetto traces. Don't use for trace analysis (use | |
| browser-window-feature-refactor chromium/chromium Refactor Chrome desktop `Browser`-scoped logic, such as `Browser` and `BrowserWindow` methods and state, into encapsulated feature controllers owned by `BrowserWindowFeatures`. | |
| chromium-docs chromium/chromium Search and reference Chromium documentation from the local docs index, including design docs, APIs, and development guides. Use when the user asks to find, locate, browse, or learn from Chromium docs about architecture, APIs, testing, GPU, | |
| experimental-test-suite-mapper chromium/chromium Finds the executable test suites (e.g., `browser_tests`, `unit_tests`) responsible for compiling and executing a specific target source code file or test file in Chromium on Linux. | |
| iterative-latency-investigation chromium/chromium Iteratively investigate the source of latency in a Chrome build or in an experiment. Coordinates the multi-agent swarm (Capture, SQL Analysis, Trace Injection) to run automated browser scenarios, capture traces, analyze them using Perfetto | |
| latency-instrumentation chromium/chromium Surgically injects trace macros (TRACE_EVENT) into Chromium C++ files to expose "black box" latency gaps, resolves headers, and compiles the browser using a self-healing loop. Strictly no performance optimizations or refactoring. | |
| modularize-chrome-browser chromium/chromium Modularize a chrome/browser/ subfolder by splitting its sources out of the monolithic //chrome/browser:browser target into dedicated source_set targets in the subfolder's own BUILD.gn. Use when the user asks to modularize, extract, or creat | |
| test-conversion chromium/chromium Workflow for converting unit tests to browser tests for Project Bedrock. Invoke this when the user wants to remove complex Browser dependencies from tests. | |
| test-conversion-researcher chromium/chromium Researcher for converting unit tests to browser tests for Project Bedrock. Invoke this when the user needs to understand the current codebase behavior while removing complex Browser dependencies from tests. | |
| test-conversion-reviewer chromium/chromium Reviewer for converting unit tests to browser tests for Project Bedrock. Invoke this when the user needs to review their work while removing complex Browser dependencies from tests. | |
| dashi-ppt chuspeeism/dashi-ppt-skill | |
| dashiai-ppt chuspeeism/dashi-ppt-skill | |
| clean-architecture ciembor/agent-rules-books Apply Robert C. Martin-inspired architecture rules when separating business policy from frameworks, databases, UI, or infrastructure details. | |
| clean-code ciembor/agent-rules-books | |
| agent-wallet-policy circlefin/skills | |
| bridge-stablecoin circlefin/skills | |
| fund-agent-wallet circlefin/skills |
5,601–5,650 of 108,174