# Mandate 2 3 7 Code Static Eval

> Evaluate static code indicators for Mandate 2.3.7 (UI/UX Behavioural Safeguards and Trust Calibration). Use when assessing partial code-evaluable controls and producing a confidence-scored static finding package before requesting runtime/process evidence.

- Skill: `jefflyt/mandate-2-3-7-code-static-eval` (Agent Skill)
- Install (CLI): `npx skillmds@latest add jefflyt/mandate-2-3-7-code-static-eval`
- Raw SKILL.md: https://api.skillmd.com/api/skills/jefflyt/mandate-2-3-7-code-static-eval/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Security
- Author: jefflyt (https://skillmd.com/u/jefflyt)
- Updated: 2026-09-10
- Page: https://skillmd.com/skills/jefflyt/mandate-2-3-7-code-static-eval

---


# Mandate 2.3.7 Code Static Evaluation Skill

## Mandate
- ID: 2.3.7
- Title: UI/UX Behavioural Safeguards and Trust Calibration

## Mitigates
- ASI09 Human-Agent Trust Exploitation

## Inputs
- Repository root path.
- Tech stack/language map.
- Optional architecture notes if provided.

## Workflow
1. Scope relevant code surfaces tied to this mandate.
2. Run mandate-specific static checks and trace source-to-sink/control paths.
3. Extract exact evidence with file/line references.
4. Classify each control as implemented, partial, or missing.
5. Produce partial-confidence findings and list required runtime/process evidence for closure.

## Mandate-Specific Static Method
1. Locate high-risk recommendation UI components and response templates.
2. Verify presence of explicit risk summaries and confidence cues.
3. Verify high-risk recommendations are visually differentiated.
4. Detect persuasive/emotionally manipulative phrases in safety-critical templates.
5. Verify standardized neutral response formats in critical flows.
6. Emit findings with UI/component path and risky language evidence.

## Output Contract
Return a single structured result with:
- mandate_id, mandate_title
- static_status: implemented|partial|missing
- confidence: low|medium|high (static-only confidence)
- evidence: list of file/line findings
- gaps: unresolved items requiring operational proof
- next_evidence_requests: runtime/process artifacts needed

## Guardrails
- Avoid final compliance pass/fail using code alone.
- Mark assumptions explicitly.
- Prefer deterministic checks over heuristics when possible.