The Agent Skills Directory

[SAFE]: The skill operates entirely within the local environment, fetching security framework definitions from a shared directory and searching the user's own codebase to provide contextually relevant examples.
[INDIRECT_PROMPT_INJECTION]: The skill processes user queries and analyzes content from the user's codebase. This creates an ingestion point where untrusted data (like code containing malicious comments) could theoretically attempt to influence the agent's output. However, the skill lacks dangerous capabilities such as network access or file writing, effectively neutralizing the risk.
[NO_CODE]: The skill contains only natural language instructions and does not include any scripts, executable binaries, or external package dependencies, significantly reducing its attack surface.

explain