The Agent Skills Directory

[NO_CODE]: The skill consists entirely of Markdown documentation and structural guidance. It does not include any scripts (Python, JavaScript, Shell), binaries, or tool-specific instructions that could be executed in a target environment.
[INDIRECT_PROMPT_INJECTION]: The skill provides a framework for handling data from external agents (inter-agent messaging). While this creates a theoretical attack surface for indirect prompt injection, the skill explicitly identifies this risk in its 'Security & Guardrails' section and mandates defensive measures such as schema strictness and semantic injection blocks.
[SAFE]: No malicious patterns, obfuscation, hardcoded credentials, or unauthorized access attempts were detected. The skill serves as a best-practices guide for secure agent coordination.

agent-protocol