Token导航 LogoToken导航

Agent Skill · 运维和基础设施

hermes-attestation-guardian(Hermes 认证监护人)

用于辅助安全审计、权限检查、凭据风险、认证流程和常见漏洞排查。它适合让 Agent 梳理敏感配置、检查依赖风险、分析鉴权逻辑或生成安全复核清单。使用时不能把工具输出直接当最终结论,涉及密钥、令牌、用户数据或生产系统时,应先确认最小权限、脱敏方式和操作边界。

hermes-attestation-guardian 是运维和基础设施类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证信息还不明确,第三方扫描已通过,按安装量在运维和基础设施类的 2,449 个 Skill 里排第 1,948。

总安装 339周安装 14GitHub Stars 962下载 111核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:hermes-attestation-guardian(Hermes 认证监护人)
来源仓库:https://github.com/prompt-security/clawsec
仓库路径:skills/hermes-attestation-guardian
安装命令:
npx skills add https://github.com/prompt-security/clawsec --skill hermes-attestation-guardian
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/prompt-security/clawsec --skill hermes-attestation-guardian

这个 Skill 是做什么的

运维和基础设施类 Skill 处理部署、监控、日志和云资源,多数需要较高的执行权限。

用于辅助安全审计、权限检查和认证流程排查。适合梳理敏感配置或分析鉴权逻辑。hermes-attestation-guardian 属于运维和基础设施类 Skill,可作为该场景下的辅助能力补充。使用时不能把工具输出直接当最终结论。涉及密钥或生产系统时应确认最小权限和脱敏方式。

适用于 Codex、Claude、Cursor 和 Gemini CLI。

来源仓库内路径:skills/hermes-attestation-guardian

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/prompt-security/clawsec --skill hermes-attesta…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

hermes-attestation-guardian 怎么安装?

在终端执行 npx skills add https://github.com/prompt-security/clawsec --skill hermes-attestation-guard…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

hermes-attestation-guardian 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

hermes-attestation-guardian 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

hermes-attestation-guardian 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

hermes-attestation-guardian 用的人多吗?

公开数据是累计安装 339 次,近一周安装 14 次,下载 111 次,GitHub 962 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

hermes-attestation-guardian 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理运维和基础设施类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

运维和基础设施类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
brainstorming

头脑风暴 · Codex、Claude

3,148,776173,131操作浏览器MIT通过
copywriting

文案写作 · Codex、Claude

1,996,72425,583需要联网MIT通过
openclaw-secure-linux-cloud

OpenClaw secure linux cloud 命令行 · Codex、Claude

1,853,08840接触敏感数据未明确未通过
xget

xget 命令行 · Codex、Claude

1,799,28040执行命令未明确未通过
requesting-code-review

代码审查请求 · Codex、Claude

1,590,144173,103权限未标注MIT通过
hermes-attestation-guardian

Hermes 认证监护人 · 本页

339962需要联网未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Hermes Attestation Guardian

IMPORTANT SCOPE:

  • This skill targets Hermes infrastructure only (CLI/Gateway/profile-managed deployments).
  • This skill is not an OpenClaw runtime hook package.

Goal

Generate deterministic Hermes posture attestations, verify them with fail-closed integrity checks, and compare baseline drift using stable severity mapping.

Mandatory release verification gate (before install)

Before treating any release install instructions as valid, verify all three inputs:

  1. checksums.json
  2. checksums.sig
  3. pinned signing public-key fingerprint
BASE="https://github.com/prompt-security/clawsec/releases/download/hermes-attestation-guardian-v0.1.0"
TMP="$(mktemp -d)"
trap 'rm -rf "$TMP"' EXIT

curl -fsSL "$BASE/checksums.json" -o "$TMP/checksums.json"
curl -fsSL "$BASE/checksums.sig" -o "$TMP/checksums.sig"
curl -fsSL "$BASE/signing-public.pem" -o "$TMP/signing-public.pem"

[ -s "$TMP/checksums.json" ] || { echo "ERROR: missing checksums.json" >&2; exit 1; }
[ -s "$TMP/checksums.sig" ] || { echo "ERROR: missing checksums.sig" >&2; exit 1; }

EXPECTED_PUBKEY_SHA256="711424e4535f84093fefb024cd1ca4ec87439e53907b305b79a631d5befba9c8"
ACTUAL_PUBKEY_SHA256="$(openssl pkey -pubin -in "$TMP/signing-public.pem" -outform DER | sha256sum | awk '{print $1}')"
[ "$ACTUAL_PUBKEY_SHA256" = "$EXPECTED_PUBKEY_SHA256" ] || {
  echo "ERROR: signing-public.pem fingerprint mismatch" >&2
  exit 1
}

openssl base64 -d -A -in "$TMP/checksums.sig" -out "$TMP/checksums.sig.bin"
openssl pkeyutl -verify -rawin -pubin -inkey "$TMP/signing-public.pem" \
  -sigfile "$TMP/checksums.sig.bin" -in "$TMP/checksums.json" >/dev/null

Hermes guard trust policy note

When installing from community sources, configure Hermes guard to use signature-aware trust (trusted signer fingerprint allowlist) rather than source-name-only trust. Unknown signer fingerprints should stay on community policy, and invalid signatures must remain blocked.

Commands

# Generate attestation (default output: ~/.hermes/security/attestations/current.json)
node scripts/generate_attestation.mjs

# Generate with explicit policy + deterministic timestamp
node scripts/generate_attestation.mjs \
  --policy ~/.hermes/security/attestation-policy.json \
  --generated-at 2026-04-15T18:00:00.000Z \
  --write-sha256

# Verify schema + canonical digest
node scripts/verify_attestation.mjs --input ~/.hermes/security/attestations/current.json

# Verify with baseline diff (baseline must be authenticated)
node scripts/verify_attestation.mjs \
  --input ~/.hermes/security/attestations/current.json \
  --baseline ~/.hermes/security/attestations/baseline.json \
  --baseline-expected-sha256 <trusted-baseline-sha256> \
  --fail-on-severity high

# Optional detached signature verification
node scripts/verify_attestation.mjs \
  --input ~/.hermes/security/attestations/current.json \
  --signature ~/.hermes/security/attestations/current.json.sig \
  --public-key ~/.hermes/security/keys/attestation-public.pem

# Refresh advisory feed verification state (fail-closed by default)
node scripts/refresh_advisory_feed.mjs

# Check advisory feed verification + feed summary
node scripts/check_advisories.mjs

# Guarded advisory-aware skill verification gate (returns 42 on advisory match without explicit confirm)
node scripts/guarded_skill_verify.mjs --skill some-skill --version 1.2.3

# Explicit operator acknowledgement path for advisory matches
node scripts/guarded_skill_verify.mjs --skill some-skill --version 1.2.3 --confirm-advisory

# Optional temporary unsigned bypass (dangerous; emergency-only)
HERMES_ADVISORY_ALLOW_UNSIGNED_FEED=1 node scripts/refresh_advisory_feed.mjs --allow-unsigned

# Preview scheduler config without mutating user schedule state
node scripts/setup_attestation_cron.mjs --every 6h --print-only

# Apply managed scheduler block
node scripts/setup_attestation_cron.mjs --every 6h --apply

# Preview advisory check scheduler config (guarded flow, print-only default)
node scripts/setup_advisory_check_cron.mjs --every 6h --skill some-skill --print-only

# Apply advisory check scheduler block (uses guarded_skill_verify flow)
node scripts/setup_advisory_check_cron.mjs --every 6h --skill some-skill --version 1.2.3 --apply

# Emergency-only: unsigned bypass for scheduled advisory checks (do not keep enabled)
node scripts/setup_advisory_check_cron.mjs --every 6h --skill some-skill --allow-unsigned --apply

WARNING: --allow-unsigned in scheduled commands is incident-response only. Remove it immediately after recovery and restore signed advisory verification.

Attestation payload (implemented)

The generator emits:

  • schema_version, platform, generated_at
  • generator metadata (skill + node version)
  • host metadata (hostname/platform/arch)
  • posture.runtime (gateway enabled flags + risky toggles)
  • posture.feed_verification status (verified|unverified|unknown) sourced from $HERMES_HOME/security/advisories/feed-verification-state.json
  • posture.integrity watched_files and trust_anchors (existence + sha256)
  • digests.canonical_sha256 over a stable canonical JSON representation

Fail-closed behavior

Verifier exits non-zero when:

  • schema validation fails
  • canonical digest algorithm is unsupported or digest binding mismatches
  • expected file sha256 mismatches (if configured)
  • detached signature verification fails (if configured)
  • baseline is provided without authenticated trust binding (--baseline-expected-sha256 and/or baseline signature + public key)
  • baseline authenticity or baseline schema/digest validation fails
  • baseline diff highest severity is at/above --fail-on-severity (default: critical)

Severity messages are emitted as INFO / WARNING / CRITICAL style lines.

Side effects

  • generate_attestation.mjs writes one JSON file (and optional .sha256) under $HERMES_HOME/security/attestations.
  • verify_attestation.mjs is read-only.
  • refresh_advisory_feed.mjs writes verified feed cache + verification state under $HERMES_HOME/security/advisories.
  • check_advisories.mjs is read-only.
  • guarded_skill_verify.mjs re-runs feed refresh/verification (same advisory cache + state side effects) and then performs advisory-aware gate checks.
  • setup_attestation_cron.mjs is read-only unless --apply is provided.
  • setup_attestation_cron.mjs --apply rewrites only the current user managed schedule block delimited by:

- # >>> hermes-attestation-guardian >>> - # <<< hermes-attestation-guardian <<<

  • setup_advisory_check_cron.mjs is read-only unless --apply is provided.
  • setup_advisory_check_cron.mjs --apply rewrites only the current user advisory-check managed schedule block delimited by:

- # >>> hermes-attestation-guardian-advisory-check >>> - # <<< hermes-attestation-guardian-advisory-check <<< - generated command path uses guarded_skill_verify.mjs (advisory-aware gate), not raw check_advisories.mjs

Advisory feed override knobs

  • Source selection: HERMES_ADVISORY_FEED_SOURCE=auto|remote|local
  • Remote artifacts: HERMES_ADVISORY_FEED_URL, HERMES_ADVISORY_FEED_SIG_URL, HERMES_ADVISORY_FEED_CHECKSUMS_URL, HERMES_ADVISORY_FEED_CHECKSUMS_SIG_URL
  • Local artifacts: HERMES_LOCAL_ADVISORY_FEED, HERMES_LOCAL_ADVISORY_FEED_SIG, HERMES_LOCAL_ADVISORY_FEED_CHECKSUMS, HERMES_LOCAL_ADVISORY_FEED_CHECKSUMS_SIG
  • Pinned key override: HERMES_ADVISORY_FEED_PUBLIC_KEY (default is built-in pinned key)
  • Optional checksum toggle: HERMES_ADVISORY_VERIFY_CHECKSUM_MANIFEST (default: enabled)
  • UNSAFE emergency bypass only: HERMES_ADVISORY_ALLOW_UNSIGNED_FEED=1

Notes

  • Hermes scan + test context is .mjs-based by design:

- runtime scripts: scripts/*.mjs - shared libraries: lib/*.mjs - regression tests: test/*.test.mjs

  • Keep .mjs paths/extensions stable so scanner scope, SBOM wiring, and test harness references stay valid.
  • Default output root is ~/.hermes/security/attestations/.
  • No destructive remediation actions (delete/restore/quarantine) are implemented.
  • Advisory feed remote URL allowlisting is not implemented in v0.0.2; operators must explicitly trust configured feed/checksum endpoints.
  • Guarded advisory version matching currently uses a lightweight comparator parser (>=, <=, >, <, =, ^, ~, wildcard *) and does not implement full npm semver range grammar (for example, OR ranges and complex comparator sets).
  • Operator policy file is optional JSON with:

- watch_files: list of file paths - trust_anchor_files: list of file paths

平台分布

Codex

38.71%
按下载量换算43

Claude

31.46%
按下载量换算35

Cursor

17.53%
按下载量换算19

Gemini CLI

10.04%
按下载量换算11

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills