anbeime/skill / antinet-agentteams/skills/security-scan
security-scan
Verified对进入系统的文件或 URL 执行安全与合规扫描,输出 pass/reject 判定与扫描报告,作为所有文档处理的强制前置关卡。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.2 KB |
| scripts/run_security_scan.py | script | 2.5 KB |
scripts/run_security_scan.py
View on GitHub#!/usr/bin/env python3
"""security-scan Skill 执行脚本(锦衣卫 / jinyiwei)。
对应 AgentTeams 子任务: security-scan
真实调用: core.runtime.AgentSession.run_stage("security-scan")
-> security.jinyiwei.JinYiWeiAgent.scan()
零外部依赖,可离线运行。证明每个 AgentTeams Worker 背后都是可执行代码,
而非规划文档。
"""
from __future__ import annotations
import os
import sys
import json
import argparse
HERE = os.path.dirname(os.path.abspath(__file__))
SKILLS_ROOT = os.path.dirname(os.path.dirname(HERE))
PKG = os.path.dirname(SKILLS_ROOT)
sys.path.insert(0, os.path.join(PKG, "core"))
from runtime import AgentSession # noqa: E402
def _safe(o):
if hasattr(o, "to_dict"):
return o.to_dict()
if isinstance(o, (list, tuple)):
return [_safe(x) for x in o]
if isinstance(o, dict):
return {k: _safe(v) for k, v in o.items()}
if isinstance(o, (str, int, float, bool)) or o is None:
return o
return str(o)
def main() -> None:
ap = argparse.ArgumentParser(description="security-scan skill runner")
ap.add_argument("--topic", default=None, help="可选:覆盖默认调研主题")
args = ap.parse_args()
sess = AgentSession(PKG)
if args.topic:
sess.cfg["project"]["topic_example"] = args.topic
result = sess.run_stage("security-scan") # {"yellows":[Card], "scan_report":{...}}
scan_report = result["scan_report"]
intercepted = scan_report.get("intercepted_papers", [])
payload = {
"skill": "security-scan",
"stage": "security-scan",
"worker": "jinyiwei(锦衣卫)",
"passed": len(intercepted) == 0,
"intercepted_count": len(intercepted),
"intercepted": _safe(intercepted),
"no_local_cache_as_production": scan_report.get("no_local_cache_as_production"),
"yellow_cards": _safe(result["yellows"]),
"scan_report": _safe(scan_report),
}
out_dir = os.path.join(PKG, "examples", "snse_survey", "skill_outputs")
os.makedirs(out_dir, exist_ok=True)
out_path = os.path.join(out_dir, "security_scan.json")
with open(out_path, "w", encoding="utf-8") as f:
json.dump(payload, f, ensure_ascii=False, indent=2)
print(f"[security-scan] verdict={'PASS' if payload['passed'] else 'REJECT'}"
f" intercepted={payload['intercepted_count']}"
f" yellows={len(payload['yellow_cards'])}")
print(f"[security-scan] -> {out_path}")
if __name__ == "__main__":
main()
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 467k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 467k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 467k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 193k | Updated | Claude CodeCodex | Verified | Install |