google-ads-transparency-center
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a bash script (
search_google_ads_transparency_center.sh) to executecurlandpython3. These commands are used for their intended purpose: making API requests and processing JSON data. - [EXTERNAL_DOWNLOADS]: The script makes network requests to
ai-factory.frevana.comwhich is the vendor's primary API endpoint. This is consistent with the skill's stated purpose of fetching advertisement data. - [CREDENTIALS_UNSAFE]: The skill manages a
FREVANA_TOKENfor authentication. It correctly advises users to set this in the environment or provide it via a flag, and it contains explicit instructions not to echo the token back to the user. No hardcoded credentials were found. - [DATA_EXFILTRATION]: The skill sends user-provided search terms (IDs, domains, tokens) to the Frevana API. While this involves sending data to a remote server, it is limited to the search parameters required for the skill to function and targets the vendor's own infrastructure.
- [DYNAMIC_EXECUTION]: The bash script uses Python one-liners via stdin to safely construct JSON payloads and validate API responses. This is a secure method for handling structured data in shell scripts and does not involve executing untrusted code.
Audit Metadata