memory-literary-analysis
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external literary source material which acts as an ingestion point for untrusted data. 1. Ingestion points: Chapter text processing in Phase 2. 2. Boundary markers: No delimiters are specified in the note templates. 3. Capability inventory: Uses write_note and edit_note for filesystem modification. 4. Sanitization: No content validation is described.
- [COMMAND_EXECUTION]: The skill uses tools like create_memory_project and write_note to manage files in the ~/basic-memory/ directory, which is appropriate for its intended use.
Audit Metadata