autobrowse
What this skill does
Browser automation via self-improving agent loops
github/browserbase - Privilege Escalation - 3.7k stars
Threat analysis
Skill info
pkg:github/browserbase/skills@6afe866?skill=autobrowseAssessments (3)
Privilege Escalation
Privilege Escalation via local-llm-review
scripts/evaluate.mjs
import "dotenv/config"; ... const ANTHROPIC_API_KEY = process.env.ANTHROPIC_API_KEY; ... const BROWSERBASE_API_KEY = process.env.BROWSERBASE_API_KEY;Excessive Agency
Excessive Agency via local-llm-review
scripts/evaluate.mjs
The agent calls browse CLI commands to navigate websites. Full trace is captured incrementally and written to disk.Excessive Agency via local-llm-review
README.md
The skill runs the inner agent, reads the trace, improves strategy.md, and repeats.Badge
Add the Anomity scan badge for autobrowse 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 autobrowse? Report an issue or request a rescan.
