> For clean Markdown of this page, append .md to its URL. For the complete documentation index, see https://www.superagent.sh/llms.txt.


Score external content before agents consume it and route the decision into the security factory.

# Security workers

Agents fetch packages, load web pages, install MCP servers, and clone repositories without reviewing any of it. Context Guardrails score every piece of external context before the agent trusts it, so agents keep full capability without inheriting untrusted input.

This feature complements **Runtime Guardrails**, which decide what an agent may do. Context Guardrails decide what an agent may consume.

PII and PHI use cases are excluded. Apply data classification and filtering before sending content to Context Guardrails.

## What gets scored

| Entity | Status | What Superagent checks |
| --- | --- | --- |
| [Web pages](https://www.superagent.sh/docs/security-workers/agent-guardrails/web-and-files) | Available | Domain identity, page behavior, and page content before the agent reads the page |
| [Email](https://www.superagent.sh/docs/security-workers/agent-guardrails/email-and-messages) | Available | Sender identity, phishing and injection patterns, attachments, and outbound links |
| [Messages](https://www.superagent.sh/docs/security-workers/agent-guardrails/email-and-messages) | Available | Text and outbound HTTPS links from SMS, WhatsApp, and social messages; media and attachments are not scanned |
| [Files](https://www.superagent.sh/docs/security-workers/agent-guardrails/web-and-files) | Available | Text and PDF contents, source identity, redirects, type consistency, encoded instructions, and prompt injection |
| [Agent skills](https://www.superagent.sh/docs/security-workers/agent-guardrails/extensions-and-packages) | Available | GitHub publisher identity, requested capabilities, scripts, hidden instructions, exfiltration, and prompt injection |
| [MCP repositories](https://www.superagent.sh/docs/security-workers/agent-guardrails/extensions-and-packages) | Available | Identity, tool descriptions, schemas, instructions, hooks, secrets, and executable behavior in a public GitHub repository |
| [Packages](https://www.superagent.sh/docs/security-workers/agent-guardrails/extensions-and-packages) | Available | Registry artifacts for npm, PyPI, Go, RubyGems, and GitHub Actions, using the same supply chain pipeline as pull request scans |
| Repositories | Covered by [repository red teaming](https://www.superagent.sh/docs/security-workers/red-team/repositories) | Agent-driven source review for vulnerabilities, backdoors, and unsafe behavior |

MCP scans inspect repository contents only. They do not connect to a live MCP endpoint or execute the server.

## How scoring works

Every entity is scored across three dimensions: who published it, how it behaves, and what it contains.

Each check returns a score from 0–100, a verdict of `safe`, `caution`, `suspicious`, or `dangerous`, and a confidence level. Cached results are reused across organizations.

New lookups return a preliminary identity score immediately and finish the deep scan in the background. Pass `mode=full` when you need the completed result in one request.

See the page for each entity for the exact tiers, limits, and threat types.

## Use it

- **Dashboard**: open **Agents** in the sidebar, then [Context](https://www.superagent.sh/app/agents/context). Submit a web page, email, message, file URL, skill target, public GitHub MCP repository, or package coordinate and open a result to see subscores, tiers, and threats.
- **REST API**: see the [Context Guardrails API](https://www.superagent.sh/docs/api/context-guardrails).
- **MCP**: `get_context_score` for pages, `scan_email` for raw RFC 822 email, `scan_message` for SMS and WhatsApp text, `scan_file` for file URLs, `scan_skill` for agent skills, `scan_mcp` for public GitHub MCP repositories, and `scan_package` for registry packages.

## Next steps

- [Check Web pages and files](https://www.superagent.sh/docs/security-workers/agent-guardrails/web-and-files)
- [Check email and messages](https://www.superagent.sh/docs/security-workers/agent-guardrails/email-and-messages)
- [Check extensions and packages](https://www.superagent.sh/docs/security-workers/agent-guardrails/extensions-and-packages)

---
Source: https://www.superagent.sh/docs/security-workers/agent-guardrails/context
Index: https://www.superagent.sh/llms.txt