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 execute curl and python3. 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.com which 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_TOKEN for 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
Risk Level
SAFE
Analyzed
Jun 23, 2026, 07:43 AM
Security Audit — agent-trust-hub — google-ads-transparency-center