fast-browser-use
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides tools for reading and processing content from arbitrary external websites via commands like
snapshot,harvest, andsitemap(SKILL.md). Malicious instructions embedded in the HTML or DOM of these sites could attempt to influence the agent's logic. - Ingestion points: Data enters the context through
snapshot,harvest, andsitemapcommands. - Boundary markers: The instructions do not define specific delimiters to separate untrusted web content from agent instructions.
- Capability inventory: The skill has capabilities to execute shell commands (
fbu) and write to the local file system (--outputflags). - Sanitization: There is no evidence of sanitization or filtering of the extracted content before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The installation instructions require the user to download the
fast-browser-usebinary from a third-party GitHub repository (rknoche6/fast-browser-use) via the Homebrew package manager or Cargo. This repository is not a recognized trusted vendor. - [COMMAND_EXECUTION]: The skill operates by executing the
fast-browser-useorfbubinary directly within the host's shell environment.
Audit Metadata