memory-management
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use shell commands (
wc,grep,sed,ls) to interact with project memory files located in~/.claude/projects/*/memory/. These operations are limited to text processing and line counting within the intended scope of the skill's memory management purpose. - [SAFE]: No evidence of prompt injection, data exfiltration, or malicious obfuscation was found. The skill follows best practices by encouraging structured memory management and providing templates for common topics like debugging and architecture.
Audit Metadata