product-manager-toolkit
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: Analysis of the skill's scripts and documentation shows no signs of malicious code, data exfiltration, or persistence mechanisms.
- [PROMPT_INJECTION]: The skill processes external data which presents a surface for indirect prompt injection.
- Ingestion points: The
scripts/customer_interview_analyzer.pyandscripts/rice_prioritizer.pyscripts read external text and CSV files provided by the user. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between data and potential instructions within the input files.
- Capability inventory: Across all scripts, capabilities are restricted to local file reading and basic data processing. The skill does not have network access or administrative privileges.
- Sanitization: The input data undergoes regex-based pattern matching but does not include escaping or filtering designed to prevent prompt injection attacks.
Audit Metadata