memory-notes

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is purely instructional and defines a markdown-based schema for note-taking. It does not include any scripts, external dependencies, or commands that interact with the host system's shell or network.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: No evidence of credential harvesting or unauthorized data access. The file paths and URL schemes mentioned (e.g., memory://) are part of a localized, structured knowledge management system.
  • [PROMPT_INJECTION]: The instructions are focused on formatting and structure. There are no attempts to override agent safety protocols or hijack the conversation flow.
  • [INDIRECT_PROMPT_INJECTION]: While the skill defines how an agent should ingest and process structured data, it does not introduce new vulnerabilities. The potential for processing untrusted data is inherent to any memory/RAG system, and this skill provides specific formatting (square brackets and headers) that can actually help delineate data from instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 07:57 PM