| name | mandate-2-3-1-code-static-eval |
| description | Evaluate static code indicators for Mandate 2.3.1 (Comprehensive Logging and Auditing). Use when assessing partial code-evaluable controls and producing a confidence-scored static finding package before requesting runtime/process evidence. |
Mandate 2.3.1 Code Static Evaluation Skill
Mandate
- ID: 2.3.1
- Title: Comprehensive Logging and Auditing
Mitigates
- ML08 Model Skewing
- LLM10 Unbounded Consumption
- LLM06 Excessive Agency
- ASI08 Cascading Failures
- ASI10 Rogue Agents
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
- Identify security-relevant action handlers (tool calls, data writes, external calls, admin actions).
- Verify each handler emits structured audit events with actor, action, resource, timestamp, and result.
- Detect missing logs in high-risk paths.
- Verify correlation identifiers (trace/run/session IDs) for forensic reconstruction.
- Verify log redaction/masking hooks for sensitive fields.
- Emit findings for uncovered actions and weak audit schemas.
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.