cli-anything-mailchimp
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the
CLI-Anythingframework directly from the author's official GitHub repository (github.com/HKUDS). This is a legitimate download of a vendor resource required for the skill's operation. - [PROMPT_INJECTION]: The skill processes data from the Mailchimp API (such as member names and campaign content), which represents a surface for indirect prompt injection. This is a common characteristic of API integration tools and is handled at the platform level.
- Ingestion points: Mailchimp Marketing API v3.0 responses (lists, campaigns, reports, members).
- Boundary markers: Not explicitly defined in the instructions.
- Capability inventory: Executes subprocess commands via the
cli-anything-mailchimpCLI. - Sanitization: Not specified in the provided documentation.
- [SAFE]: Credential management follows best practices. The skill instructs users to store the
MAILCHIMP_API_KEYin an environment variable rather than hardcoding it into the instruction files or scripts.
Audit Metadata