negative-keyword-builder
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a purely instructional prompt that guides the AI to analyze search terms and generate a table. It does not contain any executable scripts, command-line operations, or network calls.
- [SAFE]: The metadata explicitly defines
mcp_access: "read", which limits the skill's ability to modify external account data. The instructions further reinforce this by repeatedly stating that the draft is read-only and requires manual approval. - [SAFE]: No obfuscation, prompt injection, or persistence mechanisms were found. All external references point to the vendor's official domain (
kelpi.ai).
Audit Metadata