skills/mem0ai/mem0/mem0-pin/Gen Agent Trust Hub

mem0-pin

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection surface identified through the ingestion of untrusted data.
  • Ingestion points: Memory content is retrieved from search_memories and get_memory tools, and user text is accepted for new pins in SKILL.md.
  • Boundary markers: No delimiters or ignore instructions are used when interpolating retrieved text into update_memory or add_memory calls.
  • Capability inventory: The skill has the ability to write to persistent memory using add_memory and update_memory in SKILL.md.
  • Sanitization: No sanitization or validation of the input text is performed.
  • [SAFE]: All tool calls and logic are consistent with the stated purpose of managing Mem0 memory priority.
  • [SAFE]: Formatting instructions for OpenCode TUI are benign and do not attempt to bypass safety filters.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 07:54 AM
Security Audit — agent-trust-hub — mem0-pin