jefflyt Mandate 2.3.2 Code Static Evaluation Skill
Mandate
- ID: 2.3.2
- Title: Anomaly Detection
Mitigates
- ML08 Model Skewing
- LLM10 Unbounded Consumption
- ASI02 Tool Misuse and Exploitation
- 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
- Detect anomaly detection modules and rule definitions.
- Verify monitored dimensions include behavior, access patterns, performance, and resource consumption.
- Verify threshold logic and alert trigger paths.
- Verify suppression/cooldown logic does not disable critical alerts.
- Verify anomalous event context is logged for investigation.
- Emit findings for missing detectors and weak alert logic.
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.