product-manager

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides documentation for installing MCP servers from official registries and well-known organizations such as Microsoft and Atlassian.\n- [PROMPT_INJECTION]: The skill facilitates the ingestion of data from external platforms like Jira and GitHub, creating a surface for potential indirect prompt injection from external content.\n
  • Ingestion points: External data retrieved from Jira, Linear, GitHub, GitLab, and Azure DevOps via MCP servers.\n
  • Boundary markers: None identified in the provided templates or instructions.\n
  • Capability inventory: General reasoning and content generation (strategy, roadmaps, PRDs) based on tool output data.\n
  • Sanitization: No explicit validation or sanitization of external tool outputs is defined in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 01:22 PM
Security Audit — agent-trust-hub — product-manager