hubspot
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to use
npx @useclawlink/cli. This command downloads and executes the official CLI package from the NPM registry at runtime. The package is managed by the verified vendor, clawlink-hq. - [COMMAND_EXECUTION]: All primary functions of the skill are implemented through shell commands executed via the ClawLink CLI to interact with HubSpot's API.
- [INDIRECT_PROMPT_INJECTION]: The skill includes an attack surface for indirect prompt injection as it ingests user-provided text to find and execute CRM actions.
- Ingestion points: The command
npx @useclawlink/cli actions hubspot "<what you want to do>"in SKILL.md passes natural language strings directly to the CLI. - Boundary markers: The skill includes a specific directive: "Reads first; confirm with the user before any write."
- Capability inventory: The skill has the capability to perform shell command execution and network operations (via the CLI) across all functions in SKILL.md.
- Sanitization: There is no explicit input sanitization provided in the markdown; the skill relies on user review of the output and manual confirmation for data modification.
Audit Metadata