teable-assistant-ops
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the
teableCLI to perform database operations. It includes an installation script (scripts/install.sh) that automates the setup of the CLI environment on the host system.\n- [EXTERNAL_DOWNLOADS]: The skill downloads and installs the@teable/clipackage from the NPM registry during the setup process. This is a vendor-provided tool from the 'teable' organization.\n- [PROMPT_INJECTION]: The skill processes untrusted data from external sources, specifically database records and SQL query results (ingestion points identified inSKILL.md). There are no instructions for sanitization or the use of boundary markers to delimit this external content. This creates an indirect prompt injection surface where malicious data within the database could influence the agent's logic. The skill has extensive capabilities, including the ability to write to the database and generate automation scripts.
Audit Metadata