The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute various shell commands using npx gitnexus, which triggers the execution of the GitNexus CLI utility.
[EXTERNAL_DOWNLOADS]: Use of the npx command results in the retrieval of the gitnexus package from the npm registry if it is not already present locally.
[DATA_EXFILTRATION]: The wiki command includes a --gist flag which, if used, publishes the generated repository documentation to a public GitHub Gist. This behavior is a documented feature of the tool for sharing documentation externally.
[INDIRECT_PROMPT_INJECTION]: The analyze command parses all source files within a repository to build a knowledge graph and generate context files (CLAUDE.md, AGENTS.md). This process constitutes an ingestion surface where content from untrusted source files is processed into instructions or context for the AI agent.
Ingestion points: All source files in the project root processed by npx gitnexus analyze.
Boundary markers: None explicitly mentioned in the skill instructions.
Capability inventory: Execution of shell commands via npx (as described in SKILL.md).
Sanitization: No specific sanitization or filtering of codebase content is described before it is converted into agent context.

gitnexus-cli