attio
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npxto download and execute the@useclawlink/clipackage from the official NPM registry. - [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to manage authentication and interact with the Attio API via the vendor's CLI.
- [INDIRECT_PROMPT_INJECTION]: The skill provides an interface to read data from Attio (contacts, companies, deals), which could theoretically contain malicious instructions if the CRM data is compromised.
- Ingestion points: Data returned from Attio actions executed via
npx @useclawlink/cli run attio. - Boundary markers: The skill explicitly instructs the agent to "read first" and "confirm with the user before any write."
- Capability inventory: Access to local credential file (
~/.clawlink/credentials.json), network communication via CLI, and CRM data modification capabilities. - Sanitization: The instructions emphasize manual user confirmation for all write operations, providing a human-in-the-loop security boundary.
Audit Metadata