The Agent Skills Directory

[SAFE]: The skill operates entirely on internal data retrieval tools such as search, query, and get_page to analyze conceptual evolution within the agent's environment.
[SAFE]: Frontmatter configuration explicitly disables data modification via mutating: false, ensuring the skill remains read-only and cannot alter user files or settings.
[SAFE]: No external network requests, hardcoded credentials, or remote code execution patterns were identified during the analysis of the instructions and configuration.
[SAFE]: Analysis of the provided instructions revealed no evidence of prompt injection, obfuscation, or persistence mechanisms. The skill maintains a clear, specialized scope for conceptual analysis.
[INDIRECT_PROMPT_INJECTION]: While the skill processes user-generated notes and external documents (via get_page and search), the risk is minimal as the skill lacks high-privilege capabilities such as network access or file-writing permissions, and it enforces strict citation and quote fidelity rules.

idea-lineage