skills/iamjosuho/memorb/memorb-born/Gen Agent Trust Hub

memorb-born

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill creates an indirect prompt injection surface during vault initialization.
  • Ingestion points: The skill reads CLAUDE.md and memorbs/context/background.md to check existing context.
  • Boundary markers: The skill lacks delimiters or specific instructions to prevent the agent from executing commands that might be embedded in the processed vault files.
  • Capability inventory: The skill has the capability to create directories and write to critical configuration files like CLAUDE.md and AGENT.md.
  • Sanitization: User-provided data from the initialization interview is written directly to the filesystem without validation or sanitization.
  • [PROMPT_INJECTION]: The skill implements a persistence mechanism by modifying CLAUDE.md and AGENT.md to include a directive ('Must read memorbs/Core.md'), which ensures specific instruction sets are loaded by the agent in future sessions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 09:48 AM
Security Audit — agent-trust-hub — memorb-born