The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted data from Gmail messages, creating a surface for indirect prompt injection.\n
Ingestion points: SKILL.md describes tools like gmail_messages_list and gmail_messages_get that read external email data.\n
Boundary markers: The instructions lack explicit delimiters or warnings to ignore instructions embedded within email bodies.\n
Capability inventory: The skill utilizes powerful tools including gmail_messages_send and gmail_messages_trash.\n
Sanitization: There is no mention of sanitizing or filtering email content before processing by the agent.\n- [EXTERNAL_DOWNLOADS]: References official vendor setup pages.\n
Directs users to https://app.hyperfx-ai.ai/mcp and https://app.hyperfx-ai.ai/integrations for required configuration. These are official resources provided by the authoring vendor.

gmail