memory-search
Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute the
memory-hubcommand. Evidence: The command flow is defined asmemory-hub search "<query>" [--context N]. - [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it interpolates user-provided query strings directly into a shell command. 1. Ingestion points: the
queryparameter. 2. Boundary markers: none. 3. Capability inventory: uses the Bash tool for execution. 4. Sanitization: no input sanitization or escaping is defined in the skill logic.
Audit Metadata