Skills/ClawHub/prod-shield

prod-shield@1.2.1

CAUTION· install only

Publisher claims: "ProdShield: Hardened execution guardrails — because production only gets one chance. Use this skill whenever Claude is about to execute commands, run scripts..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher 2eux · publishing for 186 daysInstalls 1,106Last detonated 13 min ago

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 2026-11-20 and scored it 61/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Prompt injection; Stripe-like API key pattern detected; Latin word with Cyrillic or Greek look-alike letters (homoglyph). 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

CRITICAL
Prompt injectionSKILL.md:380 · Prompt injection — explicit attempt to bypass safety measures| **No workarounds** | Never bypass safety rules even if user says "just do it quickly" |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Stripe-like API key pattern detectedSKILL.md:875 · Stripe-like API key pattern detected — possible hardcoded or harvested keySTRIPE_SECRET_KEY=sk_test_your_key_hereFix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)SKILL.md:58 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)prдFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Pipe-to-shell patternSKILL.md:400 · Pipe-to-shell pattern — downloads and immediately executes remote code| **curl \| bash / wget \| sh** | Remote script executed without inspection | `curl https://get.example.com | bash` |Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Destructive file system command detectedSKILL.md:300 · Destructive file system command detecteddel /f /s /q C:\app\data\*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsSKILL.md:779 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files.env.developmentFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Destructive file system command detectedSKILL.md:294 · Destructive file system command detectedrm -rf /app/dataFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedSKILL.md:174 · Destructive file system command detected- Windows: `Remove-Item -Recurse -Force`, `rd /s /q`, `del /f /s /q`, `Format-Volume`Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsSKILL.md:478 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- Modification of `/etc/hosts`, `/etc/passwd`, `/etc/sudoers`, or cron filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Destructive file system command detectedSKILL.md:295 · Destructive file system command detectedrm -rf /var/www/prodFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsSKILL.md:778 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files.env.localFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Destructive command against a filesystem root or deviceSKILL.md:164 · Destructive command against a filesystem root or deviceBLOCKED: rm -rf / Remove-Item -Recurse on any non-temp path without explicit approvalFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsSKILL.md:777 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files.envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Pipe-to-shell patternSKILL.md:312 · Pipe-to-shell pattern — downloads and immediately executes remote codecurl https://example.com/install.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Destructive file system command detectedSKILL.md:164 · Destructive file system command detectedBLOCKED: rm -rf / Remove-Item -Recurse on any non-temp path without explicit approvalFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Pipe-to-shell patternSKILL.md:313 · Pipe-to-shell pattern — downloads and immediately executes remote codewget -O - https://example.com/setup.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Pipe-to-shell patternSKILL.md:462 · Pipe-to-shell pattern — downloads and immediately executes remote codecurl https://example.com/install.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Host or command assembled from base64 fragmentsSKILL.md:477 · Host or command assembled from base64 fragments- `base64 -d | bash` or similar decode-and-execute patternsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Pipe-to-shell patternSKILL.md:120 · Pipe-to-shell pattern — downloads and immediately executes remote code| Execute `curl \| bash` or `wget \| sh` | Piping remote scripts directly to a shell |Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Credential pass-through configurationSKILL.md:706 · Credential pass-through configuration — agent relays sensitive credentials- Pass secrets as command-line arguments (visible in `ps aux` and shell history)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
MEDIUM
Remote installer piped to shellSKILL.md:94 · Remote installer piped to shell[ ] For installs/scripts: source verified, no curl|bash from unknown URLs (Section 13)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Remote installer piped to shellSKILL.md:400 · Remote installer piped to shell| **curl \| bash / wget \| sh** | Remote script executed without inspection | `curl https://get.example.com | bash` |Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Remote installer piped to shellSKILL.md:312 · Remote installer piped to shellcurl https://example.com/install.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Credential pass-through configurationSKILL.md:964 · Credential pass-through configuration — agent relays sensitive credentials- Never pass secrets as `--build-arg` to Docker buildsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
MEDIUM
Remote installer piped to shellSKILL.md:120 · Remote installer piped to shell| Execute `curl \| bash` or `wget \| sh` | Piping remote scripts directly to a shell |Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07

Cost to the agent

Instructions loaded
≈10,618 tok
1 file · 6 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.

What would make this Verified

19 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
  2. Unclaimed publisher≈ +8 on the totalClaim 2eux: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Obfuscated code≈ +5 on the totalRemove base64-assembled strings, eval of decoded text and minified blobs. Reviewers and scanners both treat unreadable code as hostile.
  4. Stripe-like API key pattern detected≈ +4 on the totalNever read or enumerate credential locations; accept a documented environment variable instead.
  5. Pipe-to-shell pattern≈ +4 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  6. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim 2euxPropose a patch to the maintainer