jefflyt 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
- Scope relevant code surfaces tied to this mandate.
- Run mandate-specific static checks and trace source-to-sink/control paths.
- Extract exact evidence with file/line references.
- Classify each control as implemented, partial, or missing.
- Produce partial-confidence findings and list required runtime/process evidence for closure.
Mandate-Specific Static Method
- Locate high-risk recommendation UI components and response templates.
- Verify presence of explicit risk summaries and confidence cues.
- Verify high-risk recommendations are visually differentiated.
- Detect persuasive/emotionally manipulative phrases in safety-critical templates.
- Verify standardized neutral response formats in critical flows.
- 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.