memory-cli-ops

Pass

Audited by Gen Agent Trust Hub on Feb 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (LOW): The skill is centered around executing the local binary ./target/release/memory-cli. It also suggests modifying the PATH environment variable in troubleshooting.md. While standard for developer tools, these actions assume a trusted local environment to prevent binary hijacking.
  • [DATA_EXFILTRATION] (LOW): The troubleshooting documentation includes curl commands that transmit the $TURSO_TOKEN to the $TURSO_URL. This poses a risk of credential exfiltration if the URL variable is manipulated to point to a malicious server.
  • [PROMPT_INJECTION] (LOW): The skill exhibits a surface for indirect prompt injection (Category 8) by accepting untrusted strings for tasks and observations. Evidence Chain: 1. Ingestion points: commands.md flags like --task and --observation. 2. Boundary markers: None implemented in the command structure. 3. Capability inventory: Full execution of the memory-cli tool including storage and config modifications. 4. Sanitization: No sanitization or validation of input strings is documented.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 21, 2026, 09:21 AM