product-manager-toolkit

Fail

Audited by Gen Agent Trust Hub on Feb 15, 2026

Risk Level: HIGHPROMPT_INJECTIONNO_CODE
Full Analysis
  • Indirect Prompt Injection (HIGH): The skill processes untrusted external content that influences the agent's product strategy and requirement generation. * Ingestion points: The skill reads interview_transcript.txt and features.csv for analysis. * Boundary markers: No delimiters or instructions to ignore embedded commands are present in the documentation or templates. * Capability inventory: The analysis output directly feeds into the agent's synthesis of pain points, JTBD, and the creation of PRDs. * Sanitization: No mention of input sanitization or filtering of external content is provided.
  • Missing Files (LOW): The scripts scripts/rice_prioritizer.py and scripts/customer_interview_analyzer.py are referenced in the documentation but not included in the skill package, limiting the ability to verify their safety.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 15, 2026, 08:50 PM