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.txtandfeatures.csvfor 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.pyandscripts/customer_interview_analyzer.pyare 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