retro-marimo-pair

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill follows a well-defined, interactive process for identifying and diagnosing friction points in a pairing session. It includes explicit guardrails that prevent unauthorized file modifications.
  • [COMMAND_EXECUTION]: The skill describes using a scratchpad for API introspection via marimo._code_mode. This is a standard development practice and is confined to the local execution environment for debugging purposes.
  • [DATA_EXFILTRATION]: Access is restricted to the relevant repository (marimo-team/marimo-pair) and the internal API context. There is no evidence of unauthorized data collection or exfiltration to external domains.
  • [REMOTE_CODE_EXECUTION]: The skill does not download or execute code from untrusted or remote sources. All referenced tools and libraries belong to the vendor's ecosystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 09:27 PM
Security Audit — agent-trust-hub — retro-marimo-pair