atomic-note-to-moc
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from existing notes and configuration files within the vault.
- Ingestion points: The agent reads
AGENTS.md,../vault/SKILL.md, and various candidate MOC (Map of Content) files to resolve targets and filters (SKILL.md). - Boundary markers: The skill mentions a 'safe-write flow' and 'write boundary' for file operations, but does not specify delimiters to isolate instructions found within the note content from the agent's logic.
- Capability inventory: The skill is capable of reading and writing to files within the vault, including updating metadata, tags, and link structures.
- Sanitization: The skill relies on user approval flows and a 'safe-write' mechanism before applying any mutations to the vault, which serves as a human-in-the-loop control against malicious data manipulation.
Audit Metadata