The Agent Skills Directory

[SAFE]: The skill provides documentation and illustrative code snippets for using the Python standard library within the n8n environment. No executable scripts are included in the skill distribution.
[SAFE]: No hardcoded sensitive credentials or malicious network operations were found. The examples use standard placeholders (e.g., 'secret123', 'admin') for instructional purposes in generating authentication headers.
[SAFE]: The skill explicitly discourages the use of external libraries and remote script execution, which mitigates risks related to remote code execution and supply chain attacks.
[INDIRECT_PROMPT_INJECTION]: The skill guides users on ingesting untrusted data from external sources such as webhooks and other workflow nodes, which is a standard data ingestion surface.
Ingestion points: Data is ingested via _input.all(), _json.get("body"), and _node["Name"] as described in SKILL.md and DATA_ACCESS.md.
Boundary markers: The skill does not provide specific prompt-level boundary markers but emphasizes safe programming patterns like using .get() for dictionary access to handle malformed input.
Capability inventory: Capabilities are restricted to the Python standard library (e.g., json, re, datetime, hashlib), with instructions to use dedicated n8n nodes for network and database operations.
Sanitization: The skill provides multiple examples of using the re module for sanitizing and validating input strings (e.g., phone numbers, emails, and markdown text).

n8n-code-python