The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process macro-economic data from external Pandadata API endpoints. This ingestion creates a surface for potentially processing untrusted content. However, the skill implements defensive instructions, requiring the agent to verify indicator metadata via get_macro_detail and to distinguish between raw API values and generated inferences, which helps ensure data integrity. The ingestion points include various get_macro_* tool calls specified in SKILL.md.
[SAFE]: The skill does not contain any detected malicious patterns such as prompt injection, data exfiltration of sensitive files, or unauthorized command execution. All external references are limited to legitimate project documentation and licensing information. The skill operates within its stated purpose of financial data monitoring.

macro-monitor