obsidian-notes
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to capture, organize, and document user-provided notes, backlog items, and external data, creating an attack surface for instructions embedded in processed data.
- Ingestion points: The skill ingests data from the local DEV-OBSIDIAN vault files, external URLs (via the defuddle skill), and CSV/JSON data files (via the knap skill).
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the content it processes.
- Capability inventory: The skill has permissions to read from and write to the local filesystem at C:\Users\oscar.rondon\Documents\DEV-OBSIDIAN and can perform file search operations.
- Sanitization: There is no requirement or implementation described for sanitizing, validating, or escaping external content before it is processed by the agent or stored in the vault.
Audit Metadata