The Agent Skills Directory

[SAFE]: The skill provides utility scripts for product development workflows. All operations are local and use standard Python libraries. No signs of malicious behavior, data exfiltration, or obfuscation were found.
[SAFE]: Analytical scripts process external text and CSV data, which is an attack surface for indirect prompt injection. However, no dangerous capabilities are present to exploit this surface. Ingestion points: scripts/customer_interview_analyzer.py (interview transcripts), scripts/assumption_mapper.py (assumption CSVs), scripts/rice_prioritizer.py (feature CSVs). Boundary markers: None (scripts process raw input content directly). Capability inventory: Local file system read/write via Python's open() and csv modules. No network or subprocess execution capabilities. Sanitization: None (standard text processing for pattern matching and scoring).

discovery