The Agent Skills Directory

[SAFE]: No security issues were identified. The skill's functions, such as reading vault notes and updating frontmatter, align with its stated purpose as an auditing tool.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it processes content from vault notes.
Ingestion points: Notes in Engineering/ and MOCs/ folders, and the .manifest.json file.
Boundary markers: None defined for note content.
Capability inventory: Includes obsidian_read_note, obsidian_update_frontmatter, and obsidian_rag_query.
Sanitization: No explicit sanitization or filtering of note content before processing is mentioned. However, this is considered a functional requirement for a linting tool and does not represent a malicious intent.

vault-lint