felo-search
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs search operations by interacting with the official Felo AI API endpoint at openapi.felo.ai.
- [SAFE]: API credentials are correctly managed through the FELO_API_KEY environment variable, avoiding hardcoded secrets and following standard secret management practices.
- [SAFE]: The search script (scripts/search.sh) handles basic input escaping and utilizes standard system tools (curl, sed) without any suspicious command execution, privilege escalation, or persistence mechanisms.
- [SAFE]: The skill includes clear formatting instructions for processing external search results, which helps maintain clear boundaries between tool output and agent instructions to mitigate indirect prompt injection risks.
Audit Metadata