skills/garrytan/gbrain/migrate/Gen Agent Trust Hub

migrate

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because its core functionality involves ingesting and processing external data from various third-party sources.
  • Ingestion points: Data is read from external directories and files (Obsidian vaults, Notion exports, CSV/JSON files) as described in the migration phases in SKILL.md.
  • Boundary markers: The skill's instructions lack the use of delimiters or explicit warnings to the agent to disregard instructions embedded within the source data being migrated.
  • Capability inventory: The skill utilizes tools to write content (put_page), perform searches (search), and manage metadata (add_link, add_tag), all of which could be manipulated by adversarial content in the source data.
  • Sanitization: There are no outlined procedures for sanitizing, escaping, or validating the content of the external files before the agent processes or stores them in the target system.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 12:15 AM