The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill involves the dynamic generation of a Python script (generate_report.py) designed to parse and format research data. Running dynamically generated code is a pattern that requires caution.- [INDIRECT_PROMPT_INJECTION]: The skill processes research data stored in JSON format, which likely originates from external web or API sources. This data serves as an attack surface for indirect prompt injection, where malicious instructions embedded in the data could affect the final report generation.- [COMMAND_EXECUTION]: The skill performs several file system operations, such as locating configuration files (outline.yaml), reading data files, and writing executable scripts to the local workspace.

research-report