trusty-memory

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected in the skill instructions or metadata.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface through its core memory persistence functionality.
  • Ingestion points: The mcp__trusty-memory__memory_remember tool in SKILL.md ingests arbitrary text into the persistent storage.
  • Boundary markers: Absent; the instructions do not specify the use of delimiters or 'ignore' instructions for retrieved memory content.
  • Capability inventory: The skill itself manages memory storage and retrieval but does not define or execute shell commands, network requests, or file system modifications directly.
  • Sanitization: No sanitization or validation of the stored content is described in the protocol.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 06:41 PM
Security Audit — agent-trust-hub — trusty-memory