n8n-code-python
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides templates and methods for ingesting data from external sources, creating a potential vector for indirect prompt injection where malicious instructions could be embedded in the processed data.
- Ingestion points: The skill utilizes
_input.all(),_input.first(),_input.item,_json, and_nodeto access data from preceding n8n nodes, as documented inSKILL.mdandreferences/detailed-guide.md. - Boundary markers: The code templates do not implement boundary markers or instructions to isolate untrusted data from the agent's logic.
- Capability inventory: Execution environment includes the Python standard library with modules for data transformation (e.g.,
refor regex,jsonfor parsing,base64for encoding). - Sanitization: There is no evidence of input validation or sanitization routines to prevent the execution of instructions that might be contained within the ingested data.
Audit Metadata