onboarding
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the installation of standard Python dependencies including
requests,google-ads,python-dotenv, andtabulate. It also executes local setup scripts (e.g.,oauth_server.py,setup_oauth.py) located within the skill's subdirectory to handle authentication flows. - [DYNAMIC_EXECUTION]: Connection testing is performed using inline Python execution via
python -cto verify API connectivity and retrieve basic account metadata for the user. - [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The connection tests (
get_active_ads_copy.py,account_overview.py) ingest data from external advertising platforms (Meta, Google, LinkedIn) into the agent's context. - Boundary markers: None identified in the provided instructions for handling the external API responses.
- Capability inventory: The skill has the capability to execute shell commands and Python scripts as part of the setup and testing process.
- Sanitization: The skill does not explicitly mention sanitization or filtering of the content retrieved from the external ad APIs.
Audit Metadata