The Agent Skills Directory

[SAFE]: The skill contains only instructional text for narrative mapping and lacks any executable scripts or suspicious system commands.- [CREDENTIALS_UNSAFE]: The documentation mentions an optional XAI_API_KEY for search capabilities. This is described as a configuration requirement and no actual secrets or hardcoded tokens are present in the file.- [PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources such as xAI threads and web search results (SKILL.md). While this creates an indirect prompt injection surface, the risk is negligible as the skill possesses no tools for file system modification, shell access, or other dangerous operations. The instructions do not specify boundary markers or sanitization methods for the external content.

aeon-narrative-tracker