amazon-ads-analyzer
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is to ingest and analyze Amazon Ads exports (.csv and .xlsx) and generate a local HTML report. Analysis of the skill instructions and the provided Python script confirms that all processing is intended to be performed locally within the agent's environment.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data (Amazon reports). While this presents a theoretical surface for indirect prompt injection, the risk is assessed as LOW because the data is expected to be tabular metrics. The instructions guide the agent to perform specific numeric extractions and normalization, which limits the likelihood of executing instructions embedded in data.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script (
scripts/build_report.py) to generate the HTML output. A review of this script shows it uses only standard Python libraries (argparse, json, sys, pathlib) to perform a string replacement in a template file, which is a safe and intended behavior for this tool. - [DATA_EXPOSURE]: There are no signs of credential harvesting or access to sensitive system paths. The skill explicitly states a privacy policy of local data processing and avoids making external network requests.
Audit Metadata