Pipedrive CRM (OpenClaw)

Manage Pipedrive CRM from OpenClaw using API v1, including people, organizations, deals, leads, activities, notes, pipelines, and custom endpoint actions. Us...

This skill appears to be a straightforward Pipedrive API helper: it needs either a PIPEDRIVE_API_TOKEN (query param auth) or a PIPEDRIVE_ACCESS_TOKEN (Bearer OAuth) and the PIPEDRIVE_COMPANY_DOMAIN. Before installing: (1) note the registry metadata currently does NOT declare these required environment variables or a primary credential — that's an information/visibility gap (not necessarily malicious, but unexpected). (2) Only provide a least-privilege API token or an OAuth token with minimal scopes needed for the operations you'll perform. (3) Review the included scripts (pipedrive-api.py and setup-wizard.py) yourself or run them in a safe environment: they only call pipedrive.com endpoints and do not exfiltrate data to any other domain. (4) If you need stronger assurance, ask the publisher to update registry metadata to declare required env vars and a primary credential; if that is corrected and you validate the code, the skill would appear coherent and reasonable.

Type: OpenClaw Skill Name: pipedrive-crm-openclaw Version: 0.1.0 The skill is classified as suspicious due to the `request` command in `scripts/pipedrive-api.py`, which allows the AI agent to make arbitrary HTTP requests (method, path, query, body) to the Pipedrive API. While this feature is intended for full API coverage and is explicitly documented in `SKILL.md` with safety guidelines, it presents a significant vulnerability to prompt injection. An attacker could potentially craft a prompt to instruct the agent to use this command to access sensitive Pipedrive endpoints, perform unauthorized destructive actions, or exfiltrate data if the `PIPEDRIVE_API_BASE` environment variable is misconfigured to an attacker-controlled domain, as API tokens are automatically included in all requests.