product-manager-toolkit

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides utility scripts for product management tasks that operate entirely locally. There are no network requests, remote downloads, or access to sensitive credentials or system files.
  • [SAFE]: All dependencies are restricted to the Python standard library. The scripts perform predictable text processing and calculation without dynamic execution or obfuscation.
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes user-provided interview transcripts and CSV files. This is assessed as safe because the skill lacks dangerous capabilities. Ingestion points: scripts/customer_interview_analyzer.py and scripts/rice_prioritizer.py. Boundary markers: Absent. Capability inventory: Limited to local analysis and file creation for samples. Sanitization: Input is parsed using regex for thematic extraction only.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 04:39 PM
Security Audit — agent-trust-hub — product-manager-toolkit