skills/harshanandak/forge/memory/Gen Agent Trust Hub

memory

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill consists entirely of Markdown documentation and a static JSON metadata file. It contains no scripts (Python, JavaScript, Bash), binaries, or automated command sequences.
  • [SAFE]: All instructions describe legitimate usage of a project-local memory tool (forge remember, forge recall) or interaction with an opt-in knowledge graph (Graphiti) via standard MCP (Model Context Protocol) tool calls. The mention of external backends like FalkorDB is contextual documentation for the developer and does not involve automated remote code execution. No sensitive file paths, credential exfiltration, or obfuscation patterns were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 10:07 AM
Security Audit — agent-trust-hub — memory