servicenow-docs-mcp
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: Fetches documentation from the official ServiceNow GitHub repository (github.com/ServiceNow/ServiceNowDocs). This is a well-known service and aligns with the skill's stated purpose of providing documentation search capabilities.
- [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection by ingesting and processing external documentation content.
- Ingestion points: Markdown content is retrieved via GitHub lookup (SN-Docs-Get) and local SQLite FTS5 search (SN-Docs-Search).
- Boundary markers: Absent. The instructions do not explicitly mandate delimiters or specific instructions to prevent the agent from executing commands that might be embedded in the documentation files.
- Capability inventory: The skill is associated with native capabilities including Bash, Read, and Write, which could be targeted by successful injection.
- Sanitization: Not specified; the skill instructions do not detail logic for filtering or sanitizing the retrieved documentation content before processing.
- [EXTERNAL_DOWNLOADS]: Mentions the optional use of the 'better-sqlite3' library for local indexing. This is a standard and well-known package in the Node.js ecosystem.
Audit Metadata