skills/vm0-ai/vm0-skills/airtable/Gen Agent Trust Hub

airtable

Pass

Audited by Gen Agent Trust Hub on Apr 17, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: Authentication is managed through the $AIRTABLE_TOKEN environment variable, preventing sensitive credentials from being hardcoded in the skill files.
  • [SAFE]: The skill limits its external communication to the official Airtable API domain (api.airtable.com), which is recognized as a well-known and trusted service.
  • [COMMAND_EXECUTION]: The skill utilizes standard system utilities including curl for network requests and jq for parsing JSON data. It also uses cat to create temporary request payload files in /tmp/.
  • [SAFE]: The skill exhibits an attack surface for indirect prompt injection (Category 8) because it processes potentially untrusted data from external sources. Ingestion points: Airtable records and comments fetched via API calls in SKILL.md. Boundary markers: None identified. Capability inventory: Performs network requests and writes to the local filesystem (/tmp/). Sanitization: No explicit sanitization or validation of the ingested data is present.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 17, 2026, 04:43 PM
Security Audit — agent-trust-hub — airtable