notemdpro-selection-processor

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill describes a workflow for ingesting and processing untrusted data from document selections, which constitutes an indirect prompt injection surface.
  • Ingestion points: Data enters the context via editor.getSelection() and editor.document.getText(selection) as shown in the provided code templates.
  • Boundary markers: The documentation and snippets do not define specific delimiters or 'ignore' instructions to isolate the selected text from the processing prompt.
  • Capability inventory: The skill possesses the capability to write to the file system via editor.replaceSelection() and fs.writeFileSync(), and to trigger downstream LLM actions via callLLM().
  • Sanitization: No sanitization, escaping, or validation logic is included in the provided templates to mitigate instructions hidden within processed text.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 02:49 PM
Security Audit — agent-trust-hub — notemdpro-selection-processor