The Agent Skills Directory

[PROMPT_INJECTION]: The skill involves reading session logs to generate automated documentation drafts in the wiki. This creates an indirect prompt injection surface where malicious content or instructions present in the session history could potentially influence the AI's generation of the markdown files.
[COMMAND_EXECUTION]: The instructions require the agent to perform file system operations, including creating new markdown files in llmwiki/wiki/draft/cave/ and appending data to llmwiki/wiki/index.md and llmwiki/wiki/log.md. While this is consistent with the skill's stated purpose of maintaining a documentation log, it represents an automated write capability based on session data.

caveman-stats