원클릭으로 Manus에서 모든 스킬 실행

mandate-2-4-1-code-static-eval

스타5

포크0

업데이트2026년 2월 28일 05:39

Evaluate static code indicators for Mandate 2.4.1 (Resource Consumption Limits). Use when assessing partial code-evaluable controls and producing a confidence-scored static finding package before requesting runtime/process evidence.

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

zey-2

zey-2/security_skillpacks

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

Mandate 2.4.1 Code Static Evaluation Skill

Mandate

ID: 2.4.1
Title: Resource Consumption Limits

Mitigates

LLM10 Unbounded Consumption
ASI02 Tool Misuse and Exploitation
MCP04 Tool Interference

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 all resource-intensive execution paths (agent loops, tool calls, generation endpoints).
Verify per-request and per-user limits (time, token, memory, request rate) in code/config.
Verify early warning and alert trigger code for near-threshold events.
Verify fail-safe behavior when limits are exceeded (throttle/reject/halt).
Detect bypass paths (internal APIs, debug routes, batch jobs) without limits.
Emit findings for uncovered paths and weak limit handling.

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.

이 저장소의 다른 Skills

같은 저장소

mandate-2-2-1-code-evaluation

zey-2/security_skillpacks

Evaluate compliance for Mandate 2.2.1 (AI Supply Chain Security) using repository code and configuration analysis. Use when producing deterministic pass/fail findings with severity, mapped mitigated vulnerabilities, and file-level evidence.

2026-02-285

mandate-2-2-6-code-evaluation

zey-2/security_skillpacks

Evaluate compliance for Mandate 2.2.6 (MCP Registry and Tool Integrity Pinning) using repository code and configuration analysis. Use when producing deterministic pass/fail findings with severity, mapped mitigated vulnerabilities, and file-level evidence.

2026-02-285

mandate-2-3-3-code-evaluation

zey-2/security_skillpacks

Evaluate compliance for Mandate 2.3.3 (Human Verification for Critical Actions) using repository code and configuration analysis. Use when producing deterministic pass/fail findings with severity, mapped mitigated vulnerabilities, and file-level evidence.

2026-02-285

mandate-2-3-5-code-evaluation

zey-2/security_skillpacks

Evaluate compliance for Mandate 2.3.5 (Secure Input and Goal Management) using repository code and configuration analysis. Use when producing deterministic pass/fail findings with severity, mapped mitigated vulnerabilities, and file-level evidence.

2026-02-285

mandate-2-3-6-code-evaluation

zey-2/security_skillpacks

Evaluate compliance for Mandate 2.3.6 (UI Transparency and Manifest Validation) using repository code and configuration analysis. Use when producing deterministic pass/fail findings with severity, mapped mitigated vulnerabilities, and file-level evidence.

2026-02-285

mandate-2-4-2-code-evaluation

zey-2/security_skillpacks

Evaluate compliance for Mandate 2.4.2 (Secure Output Handling) using repository code and configuration analysis. Use when producing deterministic pass/fail findings with severity, mapped mitigated vulnerabilities, and file-level evidence.

2026-02-285

name	mandate-2-4-1-code-static-eval
description	Evaluate static code indicators for Mandate 2.4.1 (Resource Consumption Limits). Use when assessing partial code-evaluable controls and producing a confidence-scored static finding package before requesting runtime/process evidence.

Mandate 2.4.1 Code Static Evaluation Skill

Mandate

ID: 2.4.1
Title: Resource Consumption Limits

Mitigates

LLM10 Unbounded Consumption
ASI02 Tool Misuse and Exploitation
MCP04 Tool Interference

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 all resource-intensive execution paths (agent loops, tool calls, generation endpoints).
Verify per-request and per-user limits (time, token, memory, request rate) in code/config.
Verify early warning and alert trigger code for near-threshold events.
Verify fail-safe behavior when limits are exceeded (throttle/reject/halt).
Detect bypass paths (internal APIs, debug routes, batch jobs) without limits.
Emit findings for uncovered paths and weak limit handling.

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.