The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a directory listing command (ls) to inspect multiple hidden directories on the local filesystem (e.g., ~/.claude/skills/, ~/.agent/skills/) to identify which companion skills are currently installed.
[EXTERNAL_DOWNLOADS]: The skill recommends the installation of additional components from the author's repository using the npx skills add command, which involves fetching and executing remote code.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it is designed to ingest and process untrusted external data, such as customer support tickets and draft articles. There are no boundary markers or instructions to ignore embedded commands within the ingested data, which could lead the agent to follow instructions hidden in the processed content.

knowledge-base