cornell-notes-prompt

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes user-supplied learning themes and inserts them into a prompt template for downstream use. This represents a surface for indirect prompt injection where a malicious input could attempt to redirect the agent's behavior.
  • Ingestion points: User-provided topic input 【主题】 interpolated into templates within SKILL.md and references/examples.md.
  • Boundary markers: The skill does not implement delimiters or explicit instructions for the AI to ignore embedded commands within the user-provided text.
  • Capability inventory: The skill is limited to text generation; it does not possess file system access, network capabilities, or tool execution permissions.
  • Sanitization: There is no evidence of input validation, escaping, or filtering applied to the user input before it is used to populate the generated prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 08:41 AM
Security Audit — agent-trust-hub — cornell-notes-prompt