The Agent Skills Directory

[SAFE]: No hardcoded credentials, malicious remote code downloads, or obfuscation techniques were identified within the skill files.
[SAFE]: The skill uses the agent-browser CLI for its primary functionality, which is consistent with its stated purpose of web browsing and interaction.
[SAFE]: The skill processes untrusted web content, which presents a surface for indirect prompt injection, though this is a necessary consequence of the skill's utility.
Ingestion points: Web content retrieved via agent-browser snapshot as described in SKILL.md.
Boundary markers: No specific boundary markers or instructions to ignore embedded commands within web content are provided.
Capability inventory: The skill allows the agent to navigate URLs, read page text, and interact with elements (click, fill, type, etc.) via the CLI.
Sanitization: No explicit sanitization of the retrieved web content is documented.

web-browser