The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface for indirect prompt injection by processing external content from Box storage.
Ingestion points: The skill reads untrusted data through tools like BOX_SEARCH_FOR_CONTENT, BOX_LIST_ITEMS_IN_FOLDER, and BOX_GET_FILE_INFORMATION (referenced in SKILL.md).
Boundary markers: There are no instructions for the agent to treat external content as data only or to ignore any embedded instructions, which could allow malicious content to influence agent behavior.
Capability inventory: The skill possesses high-impact capabilities including BOX_UPLOAD_FILE, BOX_DELETE_FOLDER, BOX_UPDATE_COLLABORATION, and BOX_CANCEL_BOX_SIGN_REQUEST (referenced in SKILL.md).
Sanitization: No evidence of sanitization or validation of the content retrieved from Box was found.
[EXTERNAL_DOWNLOADS]: The skill requires the configuration of an external, third-party MCP server to operate.
Evidence: The setup instructions in SKILL.md direct the user to add https://rube.app/mcp as an MCP server endpoint.

box-automation