The Agent Skills Directory

[SAFE]: The skill operates entirely on the local file system within a user-specified vault directory, primarily for writing markdown files.
[SAFE]: No network operations (such as curl, wget, or fetch) or external data exfiltration patterns were identified.
[SAFE]: The skill does not access sensitive credential files such as .env, .aws/credentials, or SSH keys, restricting its read access to specific project configuration files.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text and writes it to markdown files in a local vault, which is a core function of its intended note-taking purpose.
Ingestion points: User input processed via the argument-hint in SKILL.md and vault configuration data from .agent/context/knowledge-vault.md.
Boundary markers: No specific delimiters or safety instructions are applied when interpolating user content into markdown templates.
Capability inventory: File writing and directory creation via the agent's file system tools.
Sanitization: No content filtering or escaping is applied to the user-provided text before storage.

project-notes