sync-memory
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes an internal Python script
memory-manager.pyvia the shell to perform core operations such as diff detection, metadata preparation, and storage management. These calls use theCLAUDE_PLUGIN_ROOTenvironment variable to locate the skill's own scripts. - [INDIRECT_PROMPT_INJECTION]: The skill ingests session learnings and external JSON files (
insights.json,campaigns/) for batch synchronization. - Ingestion points: Files located in
~/.claude-marketing/brands/and current session context. - Boundary markers: None explicitly defined in the processing instructions.
- Capability inventory: Execution of subprocesses (
memory-manager.py) and data persistence to local files and vector databases. - Sanitization: Not explicitly documented; however, the skill primarily functions as a storage mechanism for user-generated session data.
Audit Metadata