firefox-browser
Fail
Audited by Gen Agent Trust Hub on Aug 4, 2026
Risk Level: HIGHCREDENTIALS_UNSAFEREMOTE_CODE_EXECUTIONDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [REMOTE_CODE_EXECUTION]: The
evaluateaction (found inSKILL.mdand implemented inextension/content.js) allows the AI agent to execute arbitrary JavaScript code within the context of any browser tab. This provides a direct mechanism to bypass browser security controls, manipulate page logic, or extract data beyond the scope of standard UI interactions. - [DATA_EXFILTRATION]: The
uploadFileanddropFileactions (defined inSKILL.mdand implemented inrust-cli/src/main.rs) enable the AI agent to read arbitrary files from the local filesystem by providing a local path. This capability presents a high risk of sensitive data exposure, such as SSH keys, configuration files, or private documents, if the agent is misdirected. - [CREDENTIALS_UNSAFE]: The
autoLoginfeature (SKILL.md,rust-cli/src/bin/host.rs) integrates with the user's Bitwarden vault via thebronzewardenlibrary. While it includes an optional fingerprint verification step (fprintd-verify), it fundamentally allows an AI agent to autonomously access and utilize stored credentials for authentication on any website. - [COMMAND_EXECUTION]: The native messaging host (
rust-cli/src/bin/host.rs) executes local system commands includingnotify-sendfor desktop alerts andfprintd-verifyfor biometric authentication. - [PROMPT_INJECTION]: The skill processes untrusted web content via the
getContentaction (SKILL.md). This establishes a large attack surface for indirect prompt injection, where malicious instructions embedded in a website could manipulate the agent to abuse its powerful browser control, vault access, or file system capabilities. - Ingestion points:
getContentaction (SKILL.md) reads raw web content into the agent context. - Boundary markers: Absent; the skill does not wrap content in delimiters or provide ignore-instructions warnings.
- Capability inventory:
evaluate(JS execution),autoLogin(vault access),uploadFile(file read), and various browser interactions (click,type,fillForm). - Sanitization: Absent; raw content is returned to the agent without filtering.
- [EXTERNAL_DOWNLOADS]: The skill's Rust component (
Cargo.toml) depends on thebronzewardenlibrary hosted athttps://github.com/1jehuang/bronzewarden.git. Documentation also directs users to download signed browser extensions (XPI files) from GitHub Releases.
Recommendations
- AI detected serious security threats
Audit Metadata