The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes content from the notes/ and projects/ directories, creating a surface for potential indirect prompt injection.
Ingestion points: notes/ and projects/ directories specified in the Scope section.
Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious instructions inside the files.
Capability inventory: The skill reads file contents and has the capability to write link corrections in apply mode.
Sanitization: No sanitization or validation of the ingested text content is described.
[NO_CODE]: The skill is composed entirely of natural language instructions and configuration metadata; it does not contain or reference external scripts, binaries, or package dependencies.

vault-lint