SKILLEMALL.ai
GitHub ↗ RU Sign in

BC skillguard-hardened

Security guard for OpenClaw skills, developed and maintained by rose北港（小红帽 / 猫猫帽帽）. Audits installed or incoming skills with local rules plus Zenmux AI intent review, then recommends pass, warn, block, or quarantine.

ClawHub Agent Skills author: 2404589803 v1.0.5 MIT-0 13 files body ≈ 1 415 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 61/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerInfrastructuretype 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
81/100
safety, quality, tests
Safety 60%
85
Quality 40%
76
Run on models
none yet
Process rating
C
61/100
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.

Exfiltration 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

Instruction override 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 text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.

For the author

An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.

How to improve

  1. 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 · 3

✓ No critical or high findings

Medium and low: 3
  • medium Exfiltration net-redirectable-api-key lib/ai_audit.py:116
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • medium Instruction override en-ignore-previous lib/discovery.py:17
    Instruction-override phrase ("ignore previous instructions") (detector / deny-list definition)
    r"ignore previous instructions|system prompt|developer message|exfiltrate|send the contents of",
    detector
  • medium Instruction override en-ignore-previous policies/default_rules.json:181
    Instruction-override phrase ("ignore previous instructions") (detector / deny-list definition)
    "pattern": "(ignore previous instructions|system prompt|developer message|exfiltrate|send the contents of)",
    detector

Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 61/100

  • 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
  • 30Running it twice. 9 mutating operations with no state check
  • 100Tools and files. No external tools needed
  • 100Steps. 18 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1415 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

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
  • +2Single-language instructions
  • +3Description length 216: enough signal without eating the budget
  • +4Structure: 14 headings
  • +3Step-by-step instructions: 18 items
  • +4Has examples (8 code blocks)
  • +3All 3 scripts are documented
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.

External checks

ClawHub: suspicious
This is a real security management skill, but it needs review because it can run arbitrary commands, move or delete skill directories, and send scanned skill content to a remote AI provider.
LLM: suspicious (high) · VirusTotal: · 29 May 2026