content-curator-skill

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary purpose is content management and quality assurance within a local knowledge management system (Obsidian).
  • [PROMPT_INJECTION]: Indirect prompt injection surface detected as the skill processes untrusted user data (notes).
  • Ingestion points: Reads files from the Obsidian vault using Read, Grep, and Glob tools.
  • Boundary markers: Absent; there are no explicit instructions to use delimiters or ignore instructions embedded within the notes being analyzed.
  • Capability inventory: The agent has the ability to modify the file system using Write and Edit tools.
  • Sanitization: Absent; no content validation or filtering is performed on the notes before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 03:37 PM