The Agent Skills Directory

[COMMAND_EXECUTION] (SAFE): The skill utilizes standard shell utilities (ls, find, cat, grep, test) to perform basic file system validation and verify the structure of documentation data. These operations are diagnostic, limited to a local output directory, and do not involve administrative privileges.
[PROMPT_INJECTION] (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8) due to the following factors: 1. Ingestion points: It processes documentation files from 'output/_data/' which are populated by external scraping tools. 2. Boundary markers: The skill lacks explicit delimiters or specific instructions for the agent to isolate external content from its own execution logic. 3. Capability inventory: The skill has the ability to read from and write to the file system, as well as execute shell commands. 4. Sanitization: There is no evidence of sanitization or escaping mechanisms for documentation content before it is interpolated into the generated SKILL.md and reference files.

skill-builder