skills/clawlink-hq/skills/airtable/Gen Agent Trust Hub

airtable

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx @useclawlink/cli, which involves downloading and executing the vendor's command-line interface from the NPM registry.
  • [COMMAND_EXECUTION]: The skill relies on shell commands to interact with the Airtable API via the @useclawlink/cli tool, allowing the agent to perform data retrieval and modification tasks.
  • [DATA_EXPOSURE]: The skill manages its own authentication tokens by storing them in the user's home directory at ~/.clawlink/credentials.json. This is standard behavior for CLI-based authentication tools.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external Airtable records, which represents a potential surface for indirect prompt injection if those records contain malicious instructions. However, the skill explicitly includes a requirement to confirm with the user before performing any write operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 02:42 PM
Security Audit — agent-trust-hub — airtable