noob-mode
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and format external data, such as tool outputs and file contents, to provide plain-English translations. This introduces a surface for indirect prompt injection if external data contains malicious instructions. However, the instructions prioritize user understanding and do not generate executable code from inputs, making the risk inherent but well-managed.\n- [SAFE]: The skill consists entirely of behavioral instructions and reference documentation. It does not include scripts, binaries, or network-active components. All referenced URLs (e.g., GitHub API) are legitimate, non-obfuscated, and consistent with the vendor author context.
Audit Metadata