activecampaign
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the
@useclawlink/clitool executed vianpxto interact with ActiveCampaign. This involves running shell commands that interface with a remote service to manage contacts, campaigns, and deals. - [INDIRECT_PROMPT_INJECTION]: The skill provides an interface where user-provided strings are passed to the CLI for action discovery and execution, creating a potential surface for injection.
- Ingestion points: User instructions are interpolated into the shell command
npx @useclawlink/cli actions activecampaign "<what you want to do>"as described inSKILL.md. - Boundary markers: The instructions include a safety guideline stating "Reads first; confirm with the user before any write," which serves as a manual confirmation boundary.
- Capability inventory: The skill possesses the ability to read, create, and update sensitive marketing data, including contacts, deal pipelines, and automations via subprocess calls to the CLI.
- Sanitization: There is no evidence of automated sanitization or escaping of the user-provided input before it is passed to the shell command.
Audit Metadata