The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute local scripts such as ./scripts/check-usage-docs-sync.sh and node scripts/generate-usage-docs.mjs using the Bash tool. These operations are intended for documentation verification and generation within the project environment.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it processes project source files and skill definitions to generate documentation. 1. Ingestion points: Source files in skills/commands/ and cli/src/commands/ as defined in the configuration. 2. Boundary markers: No specific delimiters or isolation instructions are provided to the agent for the processed content. 3. Capability inventory: The skill has access to Read, Write, and Bash tools, which allows for reading source data and executing local scripts. 4. Sanitization: There is no mention of sanitization or validation of the content extracted from project files before it is used to generate documentation.

docgen