The Agent Skills Directory

[SAFE]: The skill's instructions and provided code snippets are consistent with its purpose of generating professional financial reports. No evidence of malicious intent, unauthorized data access, or obfuscation was found.
[PROMPT_INJECTION]: The skill includes an indirect prompt injection surface because it processes untrusted financial documents and web content.
Ingestion points: External data is ingested from uploaded documents, web search, and MCP server data in Phase 1 (Step 1.1).
Boundary markers: None. There are no instructions to use specific delimiters or ignore instructions within source data.
Capability inventory: The skill utilizes an external xlsx manipulation tool and web search capabilities.
Sanitization: None. The skill focuses on extraction and formatting rather than content filtering.
[COMMAND_EXECUTION]: The skill provides Python code templates for the agent to use with the xlsx tool. These patterns are standard for programmatically building Excel models and do not involve arbitrary command execution.

datapack-builder