SKILLEMALL.ai
GitHub ↗ RU Sign in

BF clawstrike

Security audit and threat model for OpenClaw gateway hosts. Use to verify OpenClaw configuration, exposure, skills/plugins, filesystem hygiene, and to produce an OK/VULNERABLE report with evidence and fixes.

modbender/skill-library-mcp Agent Skills author: modbender MIT 1 file body ≈ 838 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Security audit and threat model for OpenClaw gateway hosts.

As a process F 32/100 · Will not run — References files that are not bundled: scripts/collect_verified.sh, references/report-format.md, references/required-checks.md

IntegrationSecurityData and analyticstype 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
87/100
safety, quality, tests
Safety 60%
99
Quality 40%
68
Run on models
none yet
Process rating
F
32/100
Will not run
References files that are not bundled: scripts/collect_verified.sh, references/report-format.md, references/required-checks.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
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 · 1

✓ No critical or high findings

Medium and low: 1
  • low Dangerous commands cmd-pipe-to-shell SKILL.md:14
    Downloads and executes remote code from an unrecognised host (pipe to shell) (negated — the text forbids it)
    3. Never run remote content (no curl|bash, wget, Invoke-WebRequest, installers, package managers, update scripts).
    negated

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: scripts/collect_verified.sh
  • warning missing-ref reference to a missing file: references/report-format.md
  • warning missing-ref reference to a missing file: references/required-checks.md
  • warning missing-ref reference to a missing file: references/threat-model.md
  • warning missing-ref reference to a missing file: references/evidence-template.md
  • warning missing-ref reference to a missing file: references/gateway.md
  • warning missing-ref reference to a missing file: references/discovery.md
  • warning missing-ref reference to a missing file: references/canvas-browser.md
  • warning missing-ref reference to a missing file: references/network.md
  • warning missing-ref reference to a missing file: references/verified-allowlist.md
  • warning missing-ref reference to a missing file: references/channels.md
  • warning missing-ref reference to a missing file: references/tools.md
  • warning missing-ref reference to a missing file: references/filesystem.md
  • warning missing-ref reference to a missing file: references/supply-chain.md
  • warning missing-ref reference to a missing file: references/config-keys.md
  • warning missing-ref reference to a missing file: references/redaction.md
  • warning missing-ref reference to a missing file: references/version-risk.md

Process rating: all ten parameters 32/100

Will not run. References files that are not bundled: scripts/collect_verified.sh, references/report-format.md, references/required-checks.md
  • 0Tools and files. 17 referenced file(s) missing: scripts/collect_verified.sh, references/report-format.md, references/required-checks.md
  • 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
  • 30Running it twice. 1 mutating operations with no state check
  • 40Consistency. Frontmatter name (clawstrike) differs from the folder (macarena-test)
  • 60Failures and branches. 2 branches
  • 85Steps. 34 steps, 1 vague phrases
  • 100Execution cost. Instruction body is 838 tokens

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
  • +4No input/output examples
  • +1No license
  • +2Single-language instructions
  • +3Description length 207: enough signal without eating the budget
  • +4Structure: 8 headings
  • +3Step-by-step instructions: 34 items

Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.