The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted data from external spreadsheet files. * Ingestion points: Data enters the agent context through the read_xlsx and analyze_spreadsheet tools defined in the mcp section of SKILL.md. * Boundary markers: The skill templates do not utilize specific delimiters or 'ignore embedded instructions' warnings to isolate external data from the agent's logic. * Capability inventory: The skill possesses the capability to read from and write to the file system using read_xlsx and create_xlsx tools. * Sanitization: There is no evidence of input validation, escaping, or filtering applied to the content retrieved from external spreadsheets before it is processed by the AI model.

Lead Qualification