Loading…
◈ Meta-Governance

Project Compass AI Governance Policy

This policy describes how Compass governs its own use of artificial intelligence, including the Claude powered "Explain This Finding" feature, in alignment with the NIST AI Risk Management Framework and the OWASP Top 10 for LLM Applications (2025).

NIST AI RMF 1.0 OWASP LLM Top 10 2025 Anthropic Vendor
Document: AI Governance Policy, Project Compass Platform  ·  Version: 1.0  ·  Effective: July 2026
Owner: Compass Security and Compliance Team  ·  Review Cycle: Quarterly
What the AI Feature Does

The "Explain This Finding" button appears alongside flagged NIST AI RMF controls on the dashboard. When selected, Compass sends a small, structured piece of information to the Anthropic API, using Claude Haiku, and receives a concise, plain language explanation of the gap along with three recommended remediation steps. This feature currently operates only in local environments and will not be available in the standard Vercel deployment unless the appropriate environment variable has been configured.

Process flow: The browser (dashboard.html) submits a request to the proxy API (POST /api/explain, handled by serve.mjs), which calls the Anthropic API (claude-haiku-4-5) and returns the explanation for display on the page.

🖥
Browser
dashboard.html
Proxy API
POST /api/explain
(serve.mjs)
Anthropic API
claude-haiku-4-5
📋
Explanation
Rendered inline

The proxy server, serve.mjs, functions as a gatekeeper. The browser never has direct access to the API key, and the proxy determines exactly which fields are permitted to be transmitted. No session data, log content, organization name, or user identity leaves the local server at any point.

What Is Sent to Anthropic, and What Is Not
Data Field Sent to Claude? Classification Notes
control_id (e.g. GV.PO-1) ✓ YES Public standard A NIST control identifier, not specific to any organization
control_name (e.g. "AI Risk Policy") ✓ YES Public standard A descriptive label drawn from the public NIST framework
status (Gap / Partial / Met) ✓ YES Non-identifying A structural category value, not tied to any organization
finding_text ✓ YES Non-identifying A fixed sentence such as "Control X, Name, is unmet," with no organization name, log content, or user data
Organization name ✗ NO Sensitive, personal Remains within the browser session only
Log file contents ✗ NO Sensitive, operational Never leaves the browser; all processing occurs on the user's device
User name or email ✗ NO Sensitive, personal Remains within the login session and is never included in any request to the API
AI tool inventory ✗ NO Sensitive, operational Remains within the session and is never included in any server call
NIST gap scores or counts ✗ NO Sensitive, operational Calculated within the browser and never transmitted
Application of NIST AI RMF to Compass Itself

Compass applies the same standard to its own AI feature that it applies when evaluating a client's AI tools. The following outlines how each relevant control applies to the "Explain This Finding" feature.

GV.PO-1 — GOVERN
AI Risk Policy
This document constitutes Compass's AI use policy for the platform. It defines the scope of the feature, the classification of data involved, accountability for the vendor relationship, and the review cadence.
Met
GV.OV-1 — GOVERN
Organizational Oversight
The Compass Security and Compliance Team owns this policy. It is reviewed on a quarterly basis, or whenever the Claude integration, its data handling, or the vendor terms change.
Met
GV.AT-1 — GOVERN
AI Awareness
Every explanation generated by the feature includes a disclosure statement identifying it as AI generated and listing exactly what was sent. Users are never left uncertain about whether they are viewing AI generated content.
Met
MP.AC-1 — MAP
Defining the AI's Role
Claude is instructed to operate solely as a concise NIST AI RMF advisor. It is not asked to perform any function outside that role, and no such function is expected of it.
Met
MS.MC-1 — MEASURE
Evaluating Trustworthiness
Every explanation is intended to be advisory rather than authoritative. The disclosure statement reminds users to verify AI guidance against official NIST documentation. No automated decisions are made on the basis of Claude's output.
Partial, advisory use only
MG.AN-1 — MANAGE
Monitoring for Incidents
Errors returned by the Anthropic API are logged locally. In a production environment, these logs should be routed to a formal monitoring system. Any inaccurate or unexpected output from Claude should be reported to the Compass team.
Partial, production logging to be established
Application of the OWASP Top 10 for LLM Applications (2025)
OWASP ID Risk Control Applied Status
LLM01:2025 Prompt Injection There is no free text field through which a user can reach the model. All content sent to Claude is drawn from a fixed set of approved fields, constructed server side rather than entered by a user, leaving no opportunity to introduce unauthorized instructions. Addressed
LLM02:2025 Sensitive Information Disclosure As shown in the data classification table above, no personal information, organization name, log content, or inventory data is transmitted. This restriction is enforced at the server level rather than the browser level. Addressed
LLM03:2025 Supply Chain Risk Anthropic is a named, contracted vendor. The specific model version, claude-haiku-4-5-20251001, is fixed within the code rather than permitted to update automatically. Vendor risk is reviewed quarterly. Addressed
LLM04:2025 Data and Model Poisoning Compass does not fine tune Claude or provide feedback that could influence future versions of the model. The integration performs read only inference. Not applicable
LLM05:2025 Improper Output Handling All output returned by Claude is safely escaped prior to being displayed, preventing execution as code. The only formatting permitted is bold text, converted from simple markdown. Addressed
LLM06:2025 Excessive Agency Claude has no access to tools, memory, or the ability to take action within this integration. It returns text only, and its output never triggers an automated action. Addressed
LLM07:2025 System Prompt Leakage The instructions provided to Claude contain no secrets, credentials, or confidential business logic. Their disclosure would not create a security risk. Addressed
LLM08:2025 Vector and Embedding Weaknesses This feature does not employ a vector database, retrieval pipeline, or embeddings of any kind. Not applicable
LLM09:2025 Misinformation Every explanation carries a label identifying it as AI generated and advising verification against official NIST documentation. The feature is described as advisory throughout, and never presented as authoritative. Residual risk remains
LLM10:2025 Unbounded Consumption Each response is limited to 400 tokens. The API key is never exposed to the browser, preventing direct or repeated calls to Anthropic from outside the server. Addressed
Anthropic: Third Party Vendor Assessment
Anthropic, PBC
Anthropic Messages API, Claude Haiku
claude-haiku-4-5-20251001
NIST control identifiers and descriptions only; no personal or organization specific data
Medium
Low
Anthropic's API usage policy may retain prompts briefly for safety monitoring purposes. Refer to Anthropic's privacy policy at api.anthropic.com/privacy.
Because only public, standard identifiers are transmitted rather than organization specific data, any information retained by the vendor carries limited sensitivity.
The API key is stored in a local .env file excluded from version control, and as an environment variable within Vercel in production. It is never committed to source control.
October 2026, in accordance with the quarterly review cycle
Responsible AI Use Statement

Compass employs artificial intelligence to support human judgment, not to replace it. The "Explain This Finding" feature is intended to help compliance professionals understand a NIST AI RMF control gap more efficiently. It does not serve as a substitute for qualified professional review, legal counsel, or official NIST documentation.

The scope of this AI feature is deliberately limited: a single function, advisory output only, no automated decision-making, and no transmission of sensitive data. This reflects the same standard of responsible AI use that Compass asks its users to apply to their own tools.

Users who observe an explanation that appears inaccurate, unexpected, or unhelpful are encouraged to report it to the Compass team. This feedback is used to refine the instructions provided to Claude or, where appropriate, to disable the feature.

This policy is reviewed on a quarterly basis. Any change affecting the data transmitted, the model in use, or the vendor relationship will be reviewed prior to deployment.