skills/nweii/agent-stuff/save-term/Gen Agent Trust Hub

save-term

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates entirely within a local environment to manage personal notes. It does not perform network operations, execute remote code, or access sensitive system credentials.\n- [PROMPT_INJECTION]: The skill ingests user-provided terms and definitions to populate vault notes, representing a standard indirect prompt injection surface for note-taking tools.\n
  • Ingestion points: User input via arguments and conversational context (SKILL.md).\n
  • Boundary markers: Content is placed into templates without specific delimiters or instructions to ignore embedded commands.\n
  • Capability inventory: Performs file reads and writes using platform tools (Write, obsidian CLI).\n
  • Sanitization: Mentions ensuring filesystem-safe filenames for punctuation, but does not specify content sanitization for Markdown or YAML.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 11:37 PM