The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to perform local command execution using PowerShell and Python scripts. It uses Invoke-WebRequest and Set-Content to manage files and network data, and executes repository-local scripts such as scripts/calendar/research_event_note_sources.py and scripts/calendar/build_event_notes.py to automate research workflows and quality checks.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection due to its automated ingestion of external web data. 1. Ingestion points: The skill retrieves content from the open web via search results and the r.jina.ai reader service. 2. Boundary markers: The instructions lack explicit delimiters or instructions for the agent to disregard potential malicious directives embedded in the scraped content. 3. Capability inventory: The skill allows the agent to write to the local filesystem and execute shell commands and scripts based on the processed data. 4. Sanitization: No sanitization, validation, or filtering mechanisms are specified for the external content before it is used by the agent to generate event descriptions.
[EXTERNAL_DOWNLOADS]: The skill performs network requests to retrieve economic data and definitions from well-known services, specifically duckduckgo.com and r.jina.ai.

xauusd-calendar-descriptions