jefflyt Mandate 2.1.2 Code Static Evaluation Skill
Mandate
- ID: 2.1.2
- Title: Secure Credential Management
Mitigates
- LLM07 System Prompt Leakage
- ASI03 Identity and Privilege Abuse
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
- Run secret scanning over source, config, prompts, and test fixtures.
- Detect credential loading patterns (
env, vault SDK, secret manager APIs). - Flag hardcoded tokens, embedded API keys, and credentials in prompt templates.
- Detect static long-lived tokens in configs and missing refresh logic.
- Check CI workflow for secret scanning and secret-leak blocking.
- Emit findings by secret type, exposure surface, and exploitability.
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.