SKILLEMALL.ai
GitHub ↗ RU Sign in

CF Tork Guardian for OpenClaw

Enterprise-grade security and governance layer for OpenClaw agents. Detect PII, enforce policies, generate compliance receipts, control tool access, and scan skills for vulnerabilities before insta...

Not recommendedcritical or high security findings
modbender/skill-library-mcp Agent Skills author: modbender MIT 31 files body ≈ 1 945 tokens Open the sourcegithub.com↗ analyzed 3 d ago

Enterprise-grade security and governance layer for OpenClaw agents.

As a process F 26/100 · Will not run — weak spots: steps, result and completion, when it triggers

AnalyzerSecurityAI and agentsInfrastructuretype 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
C
68/100
safety, quality, tests
Safety 60%
68
Quality 40%
68
Run on models
none yet
Process rating
F
26/100
Will not run
Steps w 15
0
Result and completion w 14
0
Inputs and preconditions w 11
0
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.

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. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 15

  • high Dangerous commands cmd-destructive-fs src/config.ts:20
    Destructive filesystem command (wipes root/home/drive) (string literal in code, not executed)
    ':(){:|:&};:',
    code literal
Medium and low: 14
  • low Risky intent intent-offensive-security CHANGELOG.md:16
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - **Reverse shell detection**: Pattern matching across 11+ shell signatures (bash, nc, python, perl, ruby, php, socat, mkfifo, powershell)
  • low Risky intent intent-offensive-security docs/NETWORK-SECURITY.md:108
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - **anomalies** — ports opened after startup, high connection rates, reverse shell patterns
  • low Secrets in code secret-high-entropy-token package-lock.json:25
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…7pY+zoMV…h0x/Ptw8…8dg==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:42
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…b00+Gxjx…zRc/oZwU…hzA==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:110
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha512-vHk/hA7/1Ack…wbo+jaSh…Gtl+A5zq…HFg==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:144
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…Dsc+j03S…0oA==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:433
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…NS8+tHW7…WOF+PEzk…X4Q==",
    detector
  • low Risky intent intent-offensive-security README.md:40
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    Tork Guardian governs all network activity — port binds, outbound connections, and DNS lookups — with SSRF prevention, reverse shell detection, and per-skill rate limiting.
  • low Risky intent intent-offensive-security SKILL.md:47
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    Tork Guardian governs all network activity — port binds, outbound connections, and DNS lookups — with SSRF prevention, reverse shell detection, and per-skill rate limiting.
  • low Dangerous commands cmd-privilege src/config.ts:19
    Privilege escalation / world-writable permissions (string literal in code, not executed)
    'chmod 777',
    code literal

A further 4 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 24. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 26/100

  • 0Steps. Prose only: no discrete steps
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 40Consistency. Frontmatter name (Tork Guardian for OpenClaw) differs from the folder (tork-guardian)
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 100Execution cost. Instruction body is 1945 tokens
  • 100Running it twice. No mutating operations
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 10 top-level sections: this looks like several domains in one skill

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)
  • +3No numbered steps or checklist
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 200: enough signal without eating the budget
  • +4Structure: 16 headings
  • +4Has examples (12 code blocks)
  • +4Reference files are cited in the instructions (2 of 3)

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