ServiceNow

Connect your AI agent to ServiceNow — query, create, update, and manage records across any table using the Table API and Stats API. Full CRUD operations, agg...

This skill appears to do exactly what it says: it makes REST calls to the ServiceNow instance you point it at using the SN_USER/SN_PASSWORD you provide. Before installing, verify the skill source (registry lists homepage onlyflows.tech but registry source is 'unknown' — consider checking the GitHub repo referenced in the README), and: use a dedicated, least‑privilege integration account (not an admin); prefer non-password auth (OAuth or scoped API accounts) if your instance supports it; rotate credentials used by integrations; review the bundled scripts yourself (sn.sh) to confirm behavior; be cautious when using destructive commands (delete, batch — both require --confirm) and test in a non‑production instance first. If you need higher assurance, request provenance/packaging details from the publisher or host the script from your internal repo after review.

Type: OpenClaw Skill Name: servicenow Version: 1.1.0 The OpenClaw ServiceNow skill is classified as benign. The `scripts/sn.sh` script demonstrates robust security practices, including explicit environment variable checks for credentials, URL encoding of query parameters using `jq` to prevent injection, and JSON validation for payloads. Crucially, destructive operations like `delete` and `batch` require a `--confirm` flag and `batch` defaults to dry-run mode with a safety limit. While the skill provides powerful capabilities such as full CRUD operations and file attachment management (upload/download to/from arbitrary paths), these are legitimate functions for a comprehensive ServiceNow integration and are implemented with safety measures. There is no evidence of intentional harmful behavior, data exfiltration to unauthorized endpoints, malicious execution, persistence mechanisms, or obfuscation. The `SKILL.md` instructions are clear and do not contain any malicious prompt injection attempts against the AI agent.