airtable
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the
@useclawlink/clipackage from NPM, which is executed vianpx. This is the standard delivery method for the vendor's integration tool.\n- [COMMAND_EXECUTION]: The agent is instructed to run shell commands to manage Airtable data. This includes local storage of session credentials in~/.clawlink/credentials.json.\n- [INDIRECT_PROMPT_INJECTION]: Ingesting data from Airtable bases presents a surface for indirect prompt injection, as malicious content in records could attempt to influence the agent.\n - Ingestion points: The skill retrieves data using actions like
airtable_list_recordsandairtable_get_recorddefined inSKILL.md.\n - Boundary markers: The skill does not define specific delimiters to isolate record content from agent instructions.\n
- Capability inventory: The agent can perform read and write operations on Airtable records using the CLI.\n
- Sanitization: No sanitization or validation logic is specified for the data retrieved from Airtable.
Audit Metadata