Book a 30-minute demo →
Skill scan report

bb-browser

View on GitHub
49 Medium This skill sends sensitive values to an external host. Automated analysis flagged 3 additional risk patterns.

What this skill does

Browser automation and data extraction tool that allows users to interact with websites, including private and logged-in pages, using a CLI interface. It supports fetching data with browser session co

github/epiral - Adapter Injection - 6k stars

ThreatsAdapter Injection Code Execution Data Exfiltration Tab Management and Session Hijacking

Threat analysis

Adapter Injection1 finding
Code Execution1 finding
Data Exfiltration1 finding
Tab Management and Session Hijacking1 finding

Skill info

Nameepiral/bb-browser
Registrygithub
Version7975dc7
PURLpkg:github/epiral/bb-browser@7975dc7?skill=bb-browser
Stars6k

Assessments (4)

Adapter Injection1 finding HIGH
HIGH

Adapter Injection via local-llm-review

references/site-system.md

Adapters can be stored in `~/.bb-browser/sites/` and override community adapters. This could be exploited to inject malicious adapters that perform unauthorized actions.
Code Execution1 finding HIGH
HIGH

Code Execution via local-llm-review

references/adapter-development.md

Adapters are JS files that run in the user's browser. If an adapter is malicious, it could execute arbitrary code in the user's browser context.
Data Exfiltration1 finding HIGH
HIGH

Data Exfiltration via local-llm-review

references/fetch-and-network.md

The `fetch` command allows users to make requests with browser session context, including cookies and login state. This could be used to exfiltrate sensitive data from private or logged-in pages if mi
Tab Management and Session Hijacking1 finding HIGH
HIGH

Tab Management and Session Hijacking via local-llm-review

references/site-system.md

The tool automatically manages tabs and matches them based on domain. This could be exploited to hijack sessions or perform actions in the wrong tab if not properly secured.

Badge

Add the Anomity scan badge for bb-browser to your README.

Anomity Skill Check badge

Markdown
[![Anomity Skill Check](https://anomity.ai/skills/badge.svg)](https://anomity.ai/skills/github/epiral/bb-browser/)
HTML
<a href="https://anomity.ai/skills/github/epiral/bb-browser/"><img src="https://anomity.ai/skills/badge.svg" alt="Anomity Skill Check"></a>
Image URL
https://anomity.ai/skills/badge.svg

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 bb-browser? Report an issue or request a rescan.

Ask AI about Anomity
ChatGPT Claude Perplexity Google AI Grok