product-owner

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it is designed to ingest and process data from external project management backlogs.
  • Ingestion points: Backlog data is retrieved from external services such as Jira, Trello, Azure DevOps, Linear, GitHub, and GitLab (referenced in references/integrations.md).
  • Boundary markers: The instructions do not specify any delimiters or warnings to ignore instructions embedded within the external data.
  • Capability inventory: The agent is instructed to use MCP tools or CLI tools (gh, glab, az) to perform write operations (create/update items) based on this data.
  • Sanitization: No sanitization or validation logic is defined for the external content.
  • [COMMAND_EXECUTION]: The skill explicitly instructs the agent to use command-line interface tools such as gh (GitHub), glab (GitLab), and az (Azure) to interact with project management systems if MCP servers are unavailable.
  • [EXTERNAL_DOWNLOADS]: The documentation guides the user to install and configure several external MCP servers from the npm registry and GitHub repositories. This includes both official and community-maintained servers for Atlassian, Trello, Microsoft Azure DevOps, Linear, and GitHub. These references target well-known services and trusted organizations.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 01:22 PM
Security Audit — agent-trust-hub — product-owner