SKILLEMALL.ai
GitHub ↗ RU Sign in

AC pwnclaw-security-scan

Test your AI agent for security vulnerabilities using PwnClaw. Runs 50+ attacks (prompt injection, jailbreaks, social engineering, MCP poisoning, and more) and provides fix instructions. Use when your agent needs a security check or hardening.

ClawHub Agent Skills author: Gemini2027 v1.0.0 2 files body ≈ 462 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 57/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

ReferenceAI and agentstype 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
A
91/100
safety, quality, tests
Safety 60%
98
Quality 40%
80
Run on models
none yet
Process rating
C
57/100
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

How to improve

    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 · 2

    ✓ No critical or high findings

    Medium and low: 2
    • low Risky intent intent-offensive-security skill-card.md:16
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      Developers and agent operators use this skill to run security scans against an authorized AI agent and review hardening guidance for issues such as prompt injection, jailbreaks, data exfiltration, MCP
      detector
    • low Risky intent intent-offensive-security SKILL.md:19
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Privilege Escalation & Obfuscation

    Files scanned: 2. 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 57/100

    • 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. 1 mutating operations with no state check
    • 60Failures and branches. 2 branches
    • 100Tools and files. No external tools needed
    • 100Steps. 18 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 462 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 243: enough signal without eating the budget
    • +4Structure: 9 headings
    • +3Step-by-step instructions: 18 items

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.

    External checks

    ClawHub: suspicious
    This skill is a legitimate security-testing guide, but it asks users to expose agent endpoints and adopt generated permanent instructions without enough privacy, isolation, or review guardrails.
    LLM: suspicious (high) · VirusTotal: benign · 10 Sept 2026