aitable-audit
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use
git logon specific paths to monitor changes to Aitable-related source code and configuration since the last audit date. - [EXTERNAL_DOWNLOADS]: The skill mentions using a browser-based tool (Claude-in-Chrome MCP) to access
aitable.aifor live verification of datasheets and automations, contingent on organizational policy. - [PROMPT_INJECTION]: The audit process involves ingesting data from various local files, including documentation (
docs/*.md) and source code (apps/worker/src/**/*.ts). This poses a standard surface for indirect prompt injection if the files being audited contain malicious instructions designed to influence the auditor's report.
Audit Metadata