organize
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill operates on user-generated content in the
00_收集箱/directory, which could contain instructions designed to manipulate the agent's behavior during the organization or MOC creation process. - Ingestion points: Reads tags, frontmatter, and file content from notes within the
00_收集箱/directory. - Boundary markers: Absent; the instructions do not define clear delimiters or specific instructions for the agent to ignore potentially malicious embedded content within the notes it processes.
- Capability inventory: The skill allows the agent to move files across the vault, modify YAML frontmatter (update status, keywords, description), and create new markdown files (
MOC.md) containing Dataview queries. - Sanitization: Absent; there is no mention of validating or escaping values extracted from notes (like
keywordsordescription) before they are written to the file system or included in new MOC files. Note that a human confirmation step is required for MOC creation, which serves as a partial mitigation.
Audit Metadata