supermemory-forget

Pass

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the node command to run a local script at ~/.codex/supermemory/forget-memory.js. This is the primary mechanism for the skill's functionality and is considered a standard operation for this specific toolset.
  • [PROMPT_INJECTION]: The skill accepts user-supplied text to describe what should be forgotten and places it directly into a command line argument. This creates a surface for indirect prompt injection or command injection if the input contains malicious shell characters. The instructions use double quotes around the placeholder as a boundary marker.
  • Ingestion points: The DESCRIPTION_OF_WHAT_TO_FORGET variable in the SKILL.md file.
  • Boundary markers: The placeholder is enclosed in double quotes.
  • Capability inventory: The skill can execute local scripts via the Bash tool using the node runtime.
  • Sanitization: There are no specific instructions to sanitize or escape the user input before it is passed to the shell.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 28, 2026, 03:27 AM
Security Audit — agent-trust-hub — supermemory-forget