The Agent Skills Directory

[SAFE]: The skill is composed entirely of Markdown documentation providing guidance on distributed systems concepts like consensus, replication, and backpressure.
[NO_CODE]: No executable scripts (Python, JavaScript, Shell) are included in the skill package. The only "code" present is educational pseudocode and SQL examples within the documentation files, which do not pose a runtime risk.
[PROMPT_INJECTION]: A thorough review of all 14 files reveals no attempts to override agent behavior, bypass safety filters, or extract system prompts.
[DATA_EXPOSURE_AND_EXFILTRATION]: No hardcoded credentials, sensitive file paths, or network exfiltration patterns were detected. The skill does not perform any network operations.
[OBFUSCATION]: The content is presented in clear, human-readable text. There are no instances of Base64 encoding, zero-width characters, homoglyphs, or other obfuscation techniques designed to hide malicious content.
[UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill does not download or install external packages. While it mentions technical tools like Jepsen or etcd, it does so for educational purposes and does not attempt to execute them.
[PRIVILEGE_ESCALATION]: There are no instructions or commands that attempt to acquire elevated permissions (e.g., sudo, chmod).
[DYNAMIC_CONTEXT_INJECTION]: The SKILL.md file does not use the !command syntax to execute shell commands at load time.

using-distributed-systems