prod-shield@1.2.1
CAUTION· install onlyPublisher 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.
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 deviationsStatic findings
| **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.STRIPE_SECRET_KEY=sk_test_your_key_hereFix: Never read or enumerate credential locations; accept a documented environment variable instead.prдFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.| **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.del /f /s /q C:\app\data\*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell..env.developmentFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.rm -rf /app/dataFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.- 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.- 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.rm -rf /var/www/prodFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell..env.localFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.BLOCKED: 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..envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.curl https://example.com/install.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.BLOCKED: 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.wget -O - https://example.com/setup.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.curl https://example.com/install.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.- `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.| 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.- 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.[ ] 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.| **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.curl https://example.com/install.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.- 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.| 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.Cost to the agent
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%- 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.
- 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.
- 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.
- Stripe-like API key pattern detected≈ +4 on the totalNever read or enumerate credential locations; accept a documented environment variable instead.
- Pipe-to-shell pattern≈ +4 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.