product-management

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [Prompt Injection] (SAFE): No malicious instructions, bypass attempts, or 'ignore previous instructions' patterns detected. The persona setup is appropriate for a product management assistant.
  • [Indirect Prompt Injection] (LOW): The skill is designed to process untrusted user data such as PRDs and user stories.
  • Ingestion points: User input containing product requirements, roadmaps, and feature specs.
  • Boundary markers: Absent in the provided markdown instructions.
  • Capability inventory: No executable tools, network access, or file-system writing capabilities are defined in this skill.
  • Sanitization: No explicit sanitization or validation of input data is defined. While a surface exists, the lack of capabilities prevents exploitation.
  • [No Code] (SAFE): The skill consists entirely of markdown instructions and references to internal documentation. No scripts, binaries, or package dependencies are present.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:18 PM