SKILLEMALL.ai
RU Sign in

BC configsafe

Infrastructure configuration auditor — scans Dockerfiles, K8s manifests, Terraform, and CI/CD pipelines for security misconfigurations

ClawHub Agent Skills author: suhteevah v1.0.2 MIT-0 9 files · 5 scripts body ≈ 1 967 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process C 56/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerKubernetesTerraformInfrastructuretype 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
B
86/100
safety, quality, tests
Safety 60%
90
Quality 40%
80
Run on models
none yet
Process rating
C
56/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

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.

How to improve

    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 · 6

    ✓ No critical or high findings

    Medium and low: 6
    • medium Dangerous commands cmd-pipe-to-shell scripts/patterns.sh:56
      Downloads and executes remote code from an unrecognised host (pipe to shell) (code comment)
      # curl | bash
      comment
    • low Dangerous commands cmd-pipe-to-shell README.md:99
      Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation table row; documentation of a security skill)
      | curl pipe bash | Critical | Using `curl \| bash` -- remote code execution risk |
      tablesecurity skill
    • low Dangerous commands cmd-privilege README.md:100
      Privilege escalation / world-writable permissions (documentation of a security skill)
      | chmod 777 | High | World-writable file permissions |
      security skill
    • low Dangerous commands cmd-privilege scripts/patterns.sh:64
      Privilege escalation / world-writable permissions (code comment)
      # chmod 777
      comment
    • low Dangerous commands cmd-privilege scripts/patterns.sh:65
      Privilege escalation / world-writable permissions (string literal in code, not executed)
      'chmod[[:space:]]+777|high|DF-017|chmod 777 — world-writable file permissions|Use specific permissions: chmod 755 for dirs, chmod 644 for files'
      code literal
    • low Dangerous commands cmd-privilege SKILL.md:155
      Privilege escalation / world-writable permissions (documentation of a security skill)
      | **Dockerfile** | Running as root, `latest` tag, ADD vs COPY, exposed sensitive ports, missing health checks, secrets in ENV, curl pipe bash, chmod 777, missing multi-stage builds | Critical/High |
      security skill

    Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "homepage"

    Process rating: all ten parameters 56/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
    • 100Steps. 59 steps
    • 100Failures and branches. 5 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1967 tokens
    • 100Running it twice. Mutating operations check current state

    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)
    • +3Output format is not stated: the model decides each time
    • -34 of 5 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +3Description length 134: enough signal without eating the budget
    • +4Structure: 18 headings
    • +3Step-by-step instructions: 59 items
    • +4Has examples (9 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.

    External checks

    ClawHub: suspicious
    ConfigSafe is mostly a disclosed local configuration scanner, but its license handling can run code from crafted license content and its hook feature persistently changes Git hook configuration.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026