memory-optimize
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXFILTRATION]: The skill accesses local configuration files and conversation memory located in the ~/.claude/ directory. This access is integral to the skill primary function of optimizing these files and is limited to the application's own data structures. No evidence of external data transmission was found.
- [COMMAND_EXECUTION]: The skill is granted access to the Bash tool, which is utilized for file system navigation and management within the defined project scope. Destructive actions like file deletion or modification are gated by the AskUserQuestion tool for user confirmation.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) as it processes historical conversation memory. 1. Ingestion points: ~/.claude/projects/**/memory/*.md. 2. Boundary markers: None identified in the processing logic. 3. Capability inventory: Read, Write, Edit, Glob, Grep, Bash, and Task. 4. Sanitization: No explicit sanitization of memory content is described before the LLM processes it for compression or migration.
Audit Metadata