SKILLEMALL.ai

BC tuanziguardianclaw

It serves as the ultimate defense layer, monitoring, intercepting, and blocking dangerous actions taken by other skills. TuanziGuardianClaw ensures system security by enforcing strict permission models, protecting sensitive data, preventing data exfiltration, and safeguarding against malicious or harmful operations. With advanced features like skill sandboxes, capability tokens, and real-time auditing, TuanziGuardianClaw ensures a safe and trustworthy environment for OpenClaw users.

ClawHub Agent Skills author: sawyerzm v0.1.1 MIT-0 2 files body ≈ 1 525 tokens Open the sourceclawhub.ai analyzed 4 d ago

As a process C 52/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
B
84/100
safety, quality, tests
Safety 60%
95
Quality 40%
67
Run on models
none yet
Process rating
C
52/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
When it triggers w 12
20
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.

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 · 1

✓ No critical or high findings

Medium and low: 1
  • medium Instruction override en-ignore-previous SKILL.md:201
    Instruction-override phrase ("ignore previous instructions") (documentation of a security skill)
    - ignore previous instructions
    security skill

Files scanned: 2. 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")
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 52/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 2 mutating operations with no state check
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 70Failures and branches. 5 branches
  • 100Steps. 102 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1525 tokens
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 13 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)
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • +1No license
  • +2Single-language instructions
  • +3Description length 487: enough signal without eating the budget
  • +4Structure: 32 headings
  • +3Step-by-step instructions: 102 items

Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.

External checks

ClawHub: suspicious
This defensive prompt-only skill is not malware, but it asks to act as an always-on security kernel that overrides other skills without clear platform enforcement or user-controlled scope.
LLM: suspicious (high) · VirusTotal: · 29 May 2026