cli-anything-mubu

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill provides an interface to ingest external data from document backups and synchronization logs, creating a potential surface for indirect prompt injection if the processed content contains adversarial instructions.
  • Ingestion points: File SKILL.md defines commands like docs, show, search, and changes that read local document snapshots and sync event logs.
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded content are present in the documentation.
  • Capability inventory: File SKILL.md describes mutation capabilities including create-child, delete-node, and update-text which can modify live data via the Mubu API.
  • Sanitization: No sanitization or validation routines for the ingested document content are described in the skill metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 12:02 PM
Security Audit — agent-trust-hub — cli-anything-mubu