amazon-athena
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches the
@membranehq/clipackage from the public NPM registry. This is the official tool provided by the vendor for platform interaction. - [COMMAND_EXECUTION]: Uses shell commands via the
membraneCLI to authenticate users, manage cloud connections, and run data queries. - [DATA_EXFILTRATION]: Connects to
getmembrane.comto handle authentication and action execution, which is the expected behavior for this platform-based skill. - [PROMPT_INJECTION]: Processes data retrieved from Amazon Athena. This creates a surface for indirect prompt injection, as the agent may process untrusted SQL query results.
Audit Metadata