Prompt Injection Guard（提示注入防护）
Static scan for 8 threat categories (prompt injection, hardcoded secrets, destructive commands, exfiltration, crypto-mining, privesc, persistence, obfuscation); outputs risk report + SAFE badge, fail-closed, zero-dependency. 八类威胁静态扫描（提示注入/硬编码密钥/破坏性命令/数据外泄等），输出风险报告 + SAFE 徽章，fail-closed 退出码，零依赖。
as observed 2026-11-06T15:44:01.797Z- Identifier
prompt-injection-guard- Source
- ClawHub
- Version observed
- 1.0.7
- Source repository
- not published
- Repository observation
- No source repository listed
- First observed here
- 2026-10-17T20:48:50.018Z
- Observations recorded
- 2
- Installs (reported upstream)
- 1
- Weekly downloads (upstream)
- 201
- Declared license
- MIT-0
Observation history
2026-11-06T15:44:01.797Z
Fields that differed: license changelog displayName latestVersion summary
| Field | Before | After |
|---|---|---|
license |
null | "MIT-0" |
changelog |
null | "安全面加固：permissions 声明改为与包内脚本实际能力一致；新增「数据处理边界」段，明确默认不外发、需人指定目的地并逐次确认。业务逻辑未改动。" |
displayName |
"prompt-injection-guard" | "Prompt Injection Guard（提示注入防护）" |
latestVersion |
null | "1.0.7" |
summary |
"Detect prompt injection, hardcoded secrets, destructive commands and exfiltration patterns in any text or file. 检测提示注入、硬编码密钥、破坏性命令与数据外泄模式。" | "Static scan for 8 threat categories (prompt injection, hardcoded secrets, destructive commands, exfiltration, crypto-mining, privesc, persistence, obfuscation); outputs risk repor |
Correction
If you maintain this extension and believe anything above is inaccurate, request a correction. Corrections are published, and disputed entries are marked as disputed while under review.