teable-assistant-ops
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installation process (
scripts/install.sh) and documentation (guides/cli-install.md) facilitate the installation of the@teable/clipackage from the NPM registry. As this is a vendor-owned resource (teableio), it is documented as a necessary dependency for the skill's functionality. - [COMMAND_EXECUTION]: The skill is primarily designed to execute shell commands using the
teableCLI tool to perform project-level operations such as managing tables, fields, and records. - [DYNAMIC_EXECUTION]: The skill automates the generation and deployment of JavaScript code for platform-native automations and application building (
automation generate-script,app create). While this is a core intended feature, it involves the dynamic generation of executable logic based on agent reasoning. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from Teable records and external sources via its scraping module, creating a surface for indirect prompt injection.
- Ingestion points: Data is ingested into the agent context through
record get,sql-query, andscrapeoperations across various modules. - Boundary markers: The instructions do not define explicit boundary markers or 'ignore' delimiters when processing retrieved record content.
- Capability inventory: The skill possesses significant capabilities including shell command execution, network requests (via CLI/scraper), and script writing to the platform's automation engine.
- Sanitization: No specific sanitization or filtering procedures are established for data retrieved from external platforms or database cells before it is processed by the AI.
Audit Metadata