product-manager-toolkit

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute local Python scripts (scripts/rice_prioritizer.py and scripts/customer_interview_analyzer.py) to perform feature prioritization and transcript analysis.
  • [PROMPT_INJECTION]: The skill establishes workflows that ingest and process untrusted external content, creating a vulnerability surface for indirect prompt injection.
  • Ingestion points: External text files (interview_transcript.txt) and data files (features.csv) are consumed by the analysis scripts (SKILL.md).
  • Boundary markers: The instructions lack specific delimiters or guardrail prompts to ensure the agent ignores instructions embedded within the processed data.
  • Capability inventory: The skill has the capability to run local Python scripts and output analysis results which may influence downstream agent decisions (SKILL.md).
  • Sanitization: No evidence of input validation or sanitization of the provided transcript content is mentioned in the skill definition.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 08:06 PM
Security Audit — agent-trust-hub — product-manager-toolkit