SKILLEMALL.ai
GitHub ↗ RU Sign in

FC prodshield

ProdShield: Hardened execution guardrails — because production only gets one chance. Use this skill whenever Claude is about to execute commands, run scripts, manage infrastructure, interact with databases, modify files, call APIs, delete resources, or perform any action that could affect a live system. MUST trigger for: deploy, delete, remove, drop, destroy, terminate, truncate, wipe, reset, rollback, migrate, execute, run, apply, push, publish, install, or upgrade — especially against production, live, main, or staging environments. ProdShield is the last line of defense before an irreversible mistake reaches production. Also triggers for: dependency installs, container builds, CI/CD pipeline execution, secret rotation, any action involving third-party packages or scripts, and any git commit or push that could expose API keys, passwords, tokens, private keys, database credentials, client secrets, or any sensitive credentials.

Not recommendedcritical or high security findings · low grade F
ClawHub Agent Skills author: 2eux v1.2.1 MIT-0 7 files body ≈ 10 350 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 53/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency

ProcedureGitHubInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
F
28/100
safety, quality, tests
Safety 60%
0
Quality 40%
69
Run on models
none yet
Process rating
C
53/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

Secrets in code
If you install

The files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.

For the author

The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 30

  • high Dangerous commands cmd-destructive-fs references/dangerous-commands.md:21
    Destructive filesystem command (wipes root/home/drive) (documentation of a security skill)
    :(){ :|:& };:                    # Fork bomb — crashes system
    security skill
  • high Dangerous commands cmd-encoded-exec references/dangerous-commands.md:40
    Executes a base64/encoded payload (documentation of a security skill)
    echo "base…oad" | base64 -d | bash
    security skill
  • high Dangerous commands cmd-encoded-exec references/dangerous-commands.md:41
    Executes a base64/encoded payload (documentation of a security skill)
    echo "aGVsbG8=" | base64 --decode | sh
    security skill
  • high Secrets in code secret-private-key SKILL.md:539
    Private key material (key header without key body)
    # - Private keys (-----BEGIN PRIVATE KEY----- …
    header only
Medium and low: 26
  • medium Dangerous commands cmd-destructive-fs-scoped references/dangerous-commands.md:14
    Destructive command on a partition / current directory (normal in admin docs; verify the target) (documentation of a security skill)
    dd if=/dev/zero of=/dev/sdX      # Disk wipe — NEVER in production
    security skill
  • medium Dangerous commands cmd-disable-security references/dangerous-commands.md:337
    Disables a security control (Defender, Gatekeeper, SIP, firewall, execution policy) (documentation of a security skill)
    ufw disable
    security skill
  • medium Dangerous commands cmd-disable-security references/dangerous-commands.md:338
    Disables a security control (Defender, Gatekeeper, SIP, firewall, execution policy) (documentation of a security skill)
    iptables -F                         # Flush all firewall rules
    security skill
  • medium Dangerous commands cmd-disable-security references/dangerous-commands.md:339
    Disables a security control (Defender, Gatekeeper, SIP, firewall, execution policy) (documentation of a security skill)
    setenforce 0                        # Disable SELinux enforcement
    security skill
  • medium Dangerous commands cmd-install-from-url SKILL.md:449
    Installs a package from an untrusted URL / archive (documentation of a security skill)
    # BAD:  pip install --extra-index-url http://internal.mycompany.com/ mypackage
    security skill
  • medium Secrets in code secret-private-key SKILL.md:760
    Private key material (key header without key body; documentation table row)
    | **Private keys & certificates** | `-----BEGIN PRIVATE KEY----- …
    header onlytable
  • low Dangerous commands cmd-privilege references/dangerous-commands.md:18
    Privilege escalation / world-writable permissions (documentation of a security skill)
    chmod -R 777 /                   # Dangerous permission change
    security skill
  • low Dangerous commands cmd-eval-dynamic references/dangerous-commands.md:277
    Dynamic code execution from decoded/untrusted input (documentation of a security skill)
    exec(open('downloaded_script.py').read())
    security skill
  • low Risky intent intent-offensive-security references/recovery-playbook.md:314
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    - Unexpected processes inside the container (e.g., crypto miner, reverse shell)
    detector
  • low Dangerous commands cmd-pipe-to-shell SKILL.md:94
    Downloads and executes remote code from an unrecognised host (pipe to shell) (negated — the text forbids it)
    [ ] For installs/scripts: source verified, no curl|bash from unknown URLs (Section 13)
    negated
  • low Dangerous commands cmd-pipe-to-shell SKILL.md:120
    Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation table row; documentation of a security skill)
    | Execute `curl \| bash` or `wget \| sh` | Piping remote scripts directly to a shell |
    tablesecurity skill
  • low Instruction override en-ignore-previous SKILL.md:380
    Instruction-override phrase ("ignore previous instructions") (negated — the text forbids it)
    | **No workarounds** | Never bypass safety rules even if user says "just do it quickly" |
    negated

A further 14 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 10350 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 53/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 88 mutating operations with no state check
  • 40Consistency. Frontmatter name (prodshield) differs from the folder (prod-shield)
  • 40Execution cost. Instruction body is 10350 tokens: crowds the task out of the window
  • 60Tools and files. Uses tools (bash, web, git, python, node) that frontmatter does not declare
  • 70When it triggers. States when to use, but not when not to
  • 100Steps. 82 steps
  • 100Failures and branches. 9 branches, has a failure section
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 20 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (4 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 941: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • -226 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +4Structure: 61 headings
  • +3Step-by-step instructions: 82 items
  • +4Has examples (37 code blocks)
  • +4Reference files are cited in the instructions (4 of 4)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.

External checks

ClawHub: clean
ProdShield is a markdown-only safety guardrail that asks the agent to slow down around production, credentials, destructive commands, and deployments.
LLM: benign (high) · VirusTotal: · 29 May 2026