kaneo-tracker

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting data from external sources, specifically repository-based project plans and existing Kaneo task descriptions. This creates a surface for potential indirect prompt injection where malicious instructions could be embedded in plan files or task metadata.
  • Ingestion points: Repository-grounded implementation plans and Kaneo task/project data referenced in the instructions.
  • Boundary markers: No specific delimiters or "ignore" instructions are defined for the agent when processing the ingested plan content to differentiate data from instructions.
  • Capability inventory: The skill utilizes Kaneo MCP tools to create tasks, update descriptions, manage checklists, and modify task statuses across workspaces.
  • Sanitization: There are no explicit instructions to sanitize or escape the content being moved from plans to task boards; the skill is directed to preserve the plan's level of detail in the descriptions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 04:12 AM
Security Audit — agent-trust-hub — kaneo-tracker