The Agent Skills Directory

[SAFE]: The skill provides structured guidance and local utility scripts for product management tasks such as RICE prioritization, sample size calculation, and user story generation. All operations are performed locally on the user's machine.
[DATA_EXFILTRATION]: The included Python scripts (customer_interview_analyzer.py, rice_prioritizer.py, assumption_mapper.py) read local text and CSV files provided via command-line arguments. No network operations or connections to external domains were detected, and no sensitive system paths are accessed.
[PROMPT_INJECTION]: The skill processes external data such as customer interview transcripts and product assumptions. While this represents a surface for indirect prompt injection if malicious instructions were embedded in the processed data, the logic is limited to pattern matching and statistical calculations, posing no significant risk of agent behavioral override.

product-development