SKILLEMALL.ai
GitHub ↗ RU Sign in

CC clawguard-guardian

ClawGuard Guardian v3 - Runtime guardian with behavior monitoring, interception, session freeze/replay, and emergency response

Not recommendedcritical or high security findings
ClawHub Agent Skills author: stardreaming v3.0.0 MIT-0 7 files body ≈ 2 580 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process C 54/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, failures and branches

ProcedureInfrastructuretype 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
63/100
safety, quality, tests
Safety 60%
48
Quality 40%
85
Run on models
none yet
Process rating
C
54/100
Has gaps
Inputs and preconditions w 11
0
Failures and branches w 10
0
When it triggers w 12
20
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.
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 · 10

  • high Dangerous commands cmd-destructive-fs README.md:147
    Destructive filesystem command (wipes root/home/drive) (documentation of a security skill)
    rm -rf /         # 危险删除
    security skill
  • high Dangerous commands cmd-destructive-fs README.md:149
    Destructive filesystem command (wipes root/home/drive) (documentation of a security skill)
    :(){ :|:& };:    # Fork 炸弹
    security skill
Medium and low: 8
  • medium Dangerous commands cmd-persistence SKILL.md:319
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)
    🚫 [10:30:25] Write: /etc/cron.d/malware (BLOCKED)
    security skill
  • low Dangerous commands cmd-privilege README.md:156
    Privilege escalation / world-writable permissions (documentation of a security skill)
    chmod 777        # 权限过宽
    security skill
  • low Dangerous commands cmd-privilege SKILL.md:98
    Privilege escalation / world-writable permissions (documentation table row; documentation of a security skill)
    | `chmod 777` | 🟠 HIGH | CONFIRM |
    tablesecurity skill
  • low Risky intent intent-offensive-security SKILL.md:297
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | Reverse shell | Kill + Block + Alert |

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

Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

✓ No remarks against the Agent Skills spec

Process rating: all ten parameters 54/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 1 mutating operations with no state check
  • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 100Steps. 13 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2580 tokens
  • 100Progress reporting. Reports progress
  • low 12 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)
  • -243 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +3Description length 126: enough signal without eating the budget
  • +4Structure: 38 headings
  • +3Step-by-step instructions: 13 items
  • +3Output format is stated explicitly
  • +4Has examples (17 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.

External checks

ClawHub: suspicious
This appears to be a local security/audit tool, but it overstates its protection and stores/replays operational logs with weak user controls.
LLM: suspicious (high) · VirusTotal: · 29 May 2026