credo-taste
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill operates entirely within a conversational context, guiding users through research-oriented questions without any automated interactions with the underlying operating system or network.
- [NO_CODE]: The skill package is composed strictly of Markdown instructions and local reference data. There are no executable scripts, binaries, or configuration files that could trigger code execution.
- [DATA_EXFILTRATION]: No network-capable tools or sensitive file path access patterns were identified. The skill does not attempt to read or transmit system secrets or personal user data.
- [EXTERNAL_DOWNLOADS]: The skill references external URLs for documentation and research context. These links point to reputable personal research blogs (nicholas.carlini.com) and technology podcasts (latent.space). No automated downloads or script fetches are performed from these sources.
Audit Metadata