The Agent Skills Directory

[CREDENTIALS_UNSAFE]: The file references/authentication.md contains a hardcoded API key (dot_app_UlSpzXNEXhYZIAFakHLCkMVVBLbsBIWxaRMVaJZGUOYKhDoDRZwLLvLujAIwQxbY) within an example curl command.
[PROMPT_INJECTION]: The skill implements scripts that ingest user-provided data files for transmission to a remote API, creating a vector for indirect prompt injection.
Ingestion points: Multiple scripts (send_canvas.py, send_image.py, send_text.py) ingest external data via command-line arguments like --payload, --data, --image, and --icon.
Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious instructions embedded within these external data sources.
Capability inventory: The skill possesses the capability to perform network POST and GET requests to mindreset.tech using urllib.request.
Sanitization: scripts/send_canvas.py includes several security controls, such as whitelisting allowed element types (div, span, img), blacklisting unsafe keys (__proto__, constructor, prototype), and enforcing limits on JSON nesting depth and node counts.

dot-openapi