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

mailchimp

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx to download and execute the @useclawlink/cli package from the NPM registry. This package is an official resource from the skill's author, 'clawlink-hq'.
  • [COMMAND_EXECUTION]: The skill interacts with the Mailchimp API by running shell commands through the ClawLink CLI. This includes administrative tasks such as creating, updating, and deleting audience lists and campaigns.
  • [PROMPT_INJECTION]: The skill ingests data from Mailchimp, creating a surface for potential indirect prompt injection.
  • Ingestion points: Data returned from Mailchimp via npx @useclawlink/cli run mailchimp (e.g., subscriber notes, campaign content, or list names).
  • Boundary markers: No specific delimiters or boundary markers are defined in the instructions to separate external data from agent instructions.
  • Capability inventory: The agent has the capability to execute shell commands and access the local file system for credential storage.
  • Sanitization: There is no mention of sanitization or validation of data retrieved from the Mailchimp service before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 02:43 PM
Security Audit — agent-trust-hub — mailchimp