product-manager-toolkit

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, untrusted data which creates a surface for indirect prompt injection attacks.
    • Ingestion points: The agent is instructed to process user-provided transcript files via scripts/customer_interview_analyzer.py and CSV feature lists via scripts/rice_prioritizer.py.
    • Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore or isolate natural language instructions that might be embedded within the interview transcripts or CSV descriptions.
    • Capability inventory: The skill provides Python scripts for data extraction and expects the agent to use the resulting insights to generate high-trust deliverables like Product Requirement Documents (PRDs), roadmaps, and strategic positioning statements.
    • Sanitization: The Python scripts use keyword-based heuristics and regular expressions for extraction but do not perform any sanitization, escaping, or filtering to prevent malicious instructions inside the data from influencing the agent's behavior during the synthesis phase.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 04:40 AM