librarian

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes daily files (memory/YYYY-MM-DD.md) which may contain untrusted content from outside sources.
  • Ingestion points: The skill reads daily files, MEMORY.md, and various structured files in subdirectories (people, projects, topics, decisions).
  • Boundary markers: No specific delimiters or safety warnings are used to distinguish between trusted user instructions and potentially untrusted data within the notes.
  • Capability inventory: The agent has the ability to read, create, update, and delete markdown files within the targeted directory structure (memory/).
  • Sanitization: There is no evidence of content validation or sanitization before the information is processed or moved to other files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 11:00 PM