Skills/ClawHub/ai-content-guard

ai-content-guard@1.3.3

VERIFIED· install only

Publisher claims: "AI 内容安检：检测文本、文件、网页和邮件中的提示注入、隐形字符、编码载荷和 AI 配置文件后门；纯本地确定性引擎，零网络零依赖，输出四值判决、脱敏证据与处置建议。读取来自外部或不可信来源的脚本、配置、文档、仓库代码前也先扫。" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher a9320 · publishing for 87 daysInstalls 109Last detonated 8 h ago
$clawhub install ai-content-guard
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-09 and scored it 85/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathspackage.json:31 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files…tem dirs, browser profiles, password stores, SSH keys refused; sensitive files (.env/*.pem/id_rsa/etc.) name-only reporting", "file_write": "redacted scan r…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/engine/zh_rules.py:155 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files_SENSITIVE_OBJ = (r"密钥|密码|凭据|令牌|通讯录|联系人|聊天记录|api[\s_-]?key|token|\.env|数据库备份")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsSKILL.md:205 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files浏览器配置、密码库、SSH 密钥；敏感文件（.env / *.pem / id_rsa 等）只报文件名不读内容；Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/entry.py:77 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files".env", ".env.*", "*.env", "*.pem", "*.key", "id_rsa*", "id_ed25519*",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Unicode escape sequence detectedscripts/entry.py:98 · Unicode escape sequence detected — may contain obfuscated payloads_INVISIBLE_RE = re.compile("[\u200b\u200c\u200d\u2060\ufeff\u202a-\u202e\u00ad]")Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
LOW
Prompt injectionreferences/rules.md:30 · Prompt injection — known jailbreak technique reference · informational: not an instruction file代码注释内嵌提示注入（"ignore previous instructions" / "reveal the system prompt" / 角色劫持 / dev/DAN mode）。Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Access to sensitive file pathsscripts/entry.py:82 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# 原名单只有 `.env`/`.env.*`，`secret.env` 会被当普通文本读取）Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Prompt injectionreferences/rules.md:25 · Prompt injection — explicit attempt to bypass safety measures · informational: not an instruction file- **检测特征**：仅对 AI 配置文件路径跑 10 个模式（ignore/override/disregard instructions、system prompt、you are now、DAN/dev mode、jailbreak、disable/bypass safety），每模式各计一条。Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injection attemptreferences/rules.md:30 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction file代码注释内嵌提示注入（"ignore previous instructions" / "reveal the system prompt" / 角色劫持 / dev/DAN mode）。Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Access to sensitive file pathsscripts/entry.py:81 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# 注：`*.env` 覆盖 secret.env / prod.env 等任意命名（2026-11-08 ClawHub 扫描 C 项 #14：Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈2,005 tok
1 file · 18 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.