mem-file-scan
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- COMMAND_EXECUTION (SAFE): Uses the
findcommand to search for modified markdown files. The command is scoped to the local directory and excludes sensitive or system paths like .obsidian and .trash. - DATA_EXPOSURE (SAFE): Reads local markdown files to summarize content. This is the intended behavior for an Obsidian-integrated memory skill and does not involve external network requests.
- INDIRECT_PROMPT_INJECTION (LOW): The skill ingests untrusted data from local markdown files. 1. Ingestion points: Local markdown files in the user vault; 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used when reading file contents; 3. Capability inventory: Uses the
findbash command and references themem-recordskill; 4. Sanitization: Relies on AI analysis and mandatory human confirmation (Step 6) before any data is recorded to the memory system.
Audit Metadata