qe-n8n-expression-testing
Warn
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: MEDIUMDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill includes logic in
SKILL.mdthat uses thenew Functionconstructor to evaluate JavaScript expressions from strings at runtime, allowing for the execution of arbitrary JavaScript code provided as input. - [INDIRECT_PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection by processing and executing expressions which could be supplied by untrusted external sources.
- Ingestion points: Untrusted data enters the agent context through the
expressionparameter in thevalidateExpressionSyntaxandtestExpressionfunctions. - Boundary markers: There are no markers or warnings defined to prevent the agent from executing instructions embedded in the data.
- Capability inventory: The skill has the capability to execute code via
new Functionas described inSKILL.md. - Sanitization: The logic only removes template markers (
{{and}}) but does not perform robust validation or sandboxing of the resulting JavaScript code before execution.
Audit Metadata