store-performance-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONCREDENTIALS_UNSAFEINDIRECT_PROMPT_INJECTIONPRIVILEGE_ESCALATIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The
asa.pyscript makes multiple calls tosubprocess.runto execute warehouse CLI tools such asbq,snow, anddatabricks. These calls are used to perform database queries and verify authentication states, which is central to the skill's functionality. - [CREDENTIALS_UNSAFE]: The skill interacts with sensitive local configuration and credential files. Specifically, it reads from
~/.databrickscfgto resolve Databricks host information and manages its own credential store at~/.fivetran/credentials.jsonwhere it persists Fivetran API tokens. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external Shopify tables, including customer names, product titles, and refund notes.
- Ingestion points: Data is pulled from Shopify tables (e.g.,
customer,product,order) via warehouse CLIs into the agent's context. - Boundary markers: The instructions do not define explicit boundary markers or "ignore instructions" delimiters for the data returned by these queries.
- Capability inventory: The skill has access to the
bashtool, includingpython3and various database CLIs. - Sanitization: There is no evidence of sanitization or filtering of the external data before it is presented to the agent.
- [PRIVILEGE_ESCALATION]: The instructions include a "Codex Databricks Override" logic that directs the agent to attempt rerunning commands "outside the sandbox or with elevated permissions" if specific error codes are returned by the Databricks CLI. While intended to resolve environment-specific credential caching issues, this represents a guided sandbox escape pattern.
- [DYNAMIC_EXECUTION]: The
asa.pyscript contains a developer/testing hook via theASA_FIVETRAN_FETCHERenvironment variable. If set, the script will execute the provided command string to perform HTTP requests instead of using standard libraries, allowing for dynamic command injection if the environment is compromised.
Audit Metadata