format-note
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests content from files in the user's Obsidian vault to determine tags and metadata, creating a surface for indirect instructions to influence agent behavior.
- Ingestion points: The skill reads note content from the
unpublished/folder as specified in Step 1 of the Process section inSKILL.md. - Boundary markers: There are no delimiters or explicit instructions provided to the agent to distinguish between the content to be formatted and instructions it should follow.
- Capability inventory: The agent is instructed to perform file system read and write operations (updating frontmatter and daily notes) within the scope of the
$OBSIDIAN_VAULTenvironment variable. - Sanitization: No sanitization or filtering of the ingested note content is described before the analysis phase in Step 2.
Audit Metadata