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()andeditor.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()andfs.writeFileSync(), and to trigger downstream LLM actions viacallLLM(). - Sanitization: No sanitization, escaping, or validation logic is included in the provided templates to mitigate instructions hidden within processed text.
Audit Metadata