product-manager-toolkit
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes locally provided Python scripts (
scripts/rice_prioritizer.pyandscripts/customer_interview_analyzer.py) to automate product management workflows. These scripts perform data parsing and mathematical calculations without network access or high-risk system modifications. - [PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions designed to influence the agent's behavior (Indirect Prompt Injection).
- Ingestion points: The script
scripts/customer_interview_analyzer.pyreads user-provided interview transcripts, andscripts/rice_prioritizer.pyreads feature lists from CSV files. - Boundary markers: The instructions do not define clear delimiters or use "ignore embedded instructions" warnings when processing these external data sources.
- Capability inventory: The skill possesses the ability to read from the local file system and write sample CSV files to the workspace.
- Sanitization: The Python scripts include robust path validation to prevent directory traversal attacks by ensuring all file access remains within the workspace, but they do not implement sanitization or filtering of the actual content within those files.
Audit Metadata