NYC

prompt-classification-save

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill is designed to ingest untrusted data (prompts provided by users) and perform file system operations based on that content.
  • Ingestion points: Untrusted content enters the agent context through user requests like "save this prompt" or "organize this."
  • Boundary markers: No specific boundary markers or delimiters are defined to isolate the untrusted prompt content from the agent's instructions during the saving process.
  • Capability inventory: The skill possesses file-write capabilities, specifically creating markdown files in the /Prompt栳理/ directory and appending entries to an INDEX.md file.
  • Sanitization: There is no evidence of content validation, escaping, or filtering of the user-provided prompt text before it is written to the persistent file system.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:20 PM