The Agent Skills Directory

[SAFE]: The skill implements a workflow for browser automation via the agbrowse CLI tool. It interacts with well-known and trusted AI service providers (Google, OpenAI, xAI) to perform its core functions. No instances of credential harvesting, unauthorized data exfiltration, or malicious prompt injection were identified. The use of structured envelopes for prompts is a recommended security practice to mitigate injection risks. Commands for local file access are limited to user-specified context files and templates required for the intended functionality.

web-ai