agent-user-tools

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill possesses an attack surface where untrusted data could influence agent behavior.
  • Ingestion points: Untrusted data enters the agent context through the updates object in mcp__flow-nexus__user_update_profile and the content parameter in mcp__flow-nexus__storage_upload.
  • Boundary markers: Absent. There are no instructions or delimiters provided to help the agent distinguish between its own system instructions and potentially malicious instructions embedded within user profiles or uploaded files.
  • Capability inventory: The agent has the ability to write to storage buckets (mcp__flow-nexus__storage_upload) and interact with other AI entities (mcp__flow-nexus__seraphina_chat), which could be leveraged if an injection is successful.
  • Sanitization: Absent. The skill documentation does not mention any validation, escaping, or sanitization of the data being processed or stored.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:12 PM