The Agent Skills Directory

[SAFE]: No security issues detected. The skill's behavior is consistent with its stated purpose of Gmail automation and uses legitimate browser automation tools.
[PROMPT_INJECTION]: The skill possesses an inherent attack surface for indirect prompt injection because it processes untrusted email content. Ingestion points: Extraction of email text via read_page and get_page_text in SKILL.md. Boundary markers: Absent; there are no instructions to the agent to treat email content as untrusted data or ignore instructions within it. Capability inventory: The agent can navigate, input text, and perform actions (like sending emails) via the mcp__claude-in-chrome__* tools. Sanitization: Absent.

gmail