ads-google

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill uses instructional language to guide the agent through an audit process. No patterns of jailbreaking, safety filter bypass, or instructions to disregard system rules were found.
  • [DATA_EXFILTRATION]: No network operations (such as curl or fetch) or hardcoded credentials (API keys, tokens) are present in the skill files.
  • [REMOTE_CODE_EXECUTION]: There are no scripts, package installations, or remote code execution patterns.
  • [NO_CODE]: The skill consists solely of markdown and text files, with no functional code logic or script execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external data (Google Ads reports). While it lacks specific sanitization instructions for this data, it does not possess any capabilities (like network access or file system modification) that would allow an injection to be exploited.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 02:54 AM