google-forums-search
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a bash script (
scripts/search_google_forums.sh) which in turn usescurlandpython3for network operations and JSON processing. The command execution is scoped to the skill's primary function and implements proper argument parsing and validation. - [EXTERNAL_DOWNLOADS]: The script performs POST requests to
https://ai-factory.frevana.comto fetch forum search results. This is a functional requirement for the skill's stated purpose. - [CREDENTIALS_UNSAFE]: The skill handles a
FREVANA_TOKENfor authentication. It correctly uses environment variables or command-line flags, explicitly warns against echoing the token, and includes logic to prevent token exposure in non-interactive environments. - [DATA_EXFILTRATION]: While the skill sends search queries to an external API, it is restricted to the intended search parameters. It does not attempt to access or exfiltrate sensitive local files or credentials.
Audit Metadata