The Agent Skills Directory

[SAFE]: Extensive analysis of the skill's instructions, metadata, and scripts found no indicators of malicious intent or security vulnerabilities.
[COMMAND_EXECUTION]: The skill utilizes local Python scripts for data processing tasks.
Evidence: The scripts scripts/rice_prioritizer.py and scripts/customer_interview_analyzer.py are executed via the command line to process user-provided CSV and text files. These scripts rely solely on Python standard libraries (re, json, csv, argparse, typing).
[PROMPT_INJECTION]: No attempts to override system instructions or bypass safety filters were detected.
Evidence: SKILL.md contains standard instructional content for product management frameworks and does not use any injection markers such as "Ignore previous instructions" or "Enable developer mode".
[DATA_EXPOSURE]: No hardcoded credentials or unauthorized data access patterns were identified.
Evidence: The scripts were audited for hardcoded API keys, tokens, or access to sensitive file paths (e.g., .env, .ssh), and none were found. The skill does not perform any network operations.

product-manager-toolkit