The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from external local files such as .claude/memories/about-taylor.md and project briefs in ideas/ideas/[project]/. This creates an ingestion surface for potentially untrusted content if those files are modified by external sources.
Ingestion points: Reads from .claude/memories/, my-vault/, and ideas/ directories.
Boundary markers: None specified in the instructions to delimit external content.
Capability inventory: No command execution, file-write, or network operations are defined within this skill file.
Sanitization: No explicit sanitization or validation of the ingested content is mentioned.
[SAFE]: The skill's primary purpose is organizational planning. It uses local file paths and standard workflows without invoking dangerous commands, making network requests, or using obfuscation techniques.

life-planning