linkfox-amazon-ads-manager
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data retrieved from external Amazon Ads APIs (ingestion points in all
list_*.pyscripts) and includes extensive capabilities to write or modify data on the platform (allcreate_*.pyandupdate_*.pyscripts). There are no explicit boundary markers or content sanitization procedures in place to prevent an attacker-controlled ad entity (e.g., a campaign name containing malicious instructions) from influencing the agent's behavior during subsequent management tasks. - [COMMAND_EXECUTION]: The skill utilizes
subprocess.run()withinscripts/_common.pyto execute a local script (check_auth_dependency.py). This is used for internal environment validation to ensure required authentication dependencies are met before proceeding with API operations.
Audit Metadata