SKILLEMALL.ai
GitHub ↗ RU Sign in

AC uplo-cybersecurity

AI-powered cybersecurity knowledge management. Search threat intelligence, vulnerability assessments, incident response plans, and compliance documentation with structured extraction.

ClawHub Agent Skills author: RooJenkins v1.0.0 MIT-0 5 files body ≈ 1 552 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

AnalyzerInfrastructureSecuritytype 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%
95
Quality 40%
84
Run on models
none yet
Process rating
C
61/100
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

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 · 5

    ✓ No critical or high findings

    Medium and low: 5
    • low Risky intent intent-offensive-security identity-patch.md:3
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
      You are connected to your organization's cybersecurity knowledge base through UPLO. This gives you specialized access to threat intelligence reports, vulnerability assessments, incident response plans
      quoted
    • low Risky intent intent-offensive-security identity-patch.md:5
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      Expect queries about current vulnerability scan results and remediation priorities, incident response procedures and escalation chains, security policy requirements and exceptions, penetration test fi
    • low Risky intent intent-offensive-security identity-patch.md:7
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      When presenting cybersecurity information, include CVE identifiers, severity ratings (CVSS), affected systems, and remediation timelines. For incidents, present the MITRE ATT&CK classification and con
    • low Risky intent intent-offensive-security SKILL.md:41
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
      search_with_context query="command and control C2 communication indicators previous incidents exfiltration"
      quoted
    • low Risky intent intent-offensive-security SKILL.md:86
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
      **search_with_context** — Security investigations are inherently graph problems. A single alert can connect to asset inventory records, previous incident reports, threat intelligence, and network arch
      quoted

    Files scanned: 5. 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 61/100

    • 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
    • 55Failures and branches. 1 branches
    • 100Tools and files. No external tools needed
    • 100Steps. 11 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1552 tokens
    • 100Running it twice. Mutating operations check current state
    • 100Progress reporting. Reports progress
    • 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
    • +1No license
    • +2Single-language instructions
    • +3Description length 183: enough signal without eating the budget
    • +4Structure: 8 headings
    • +3Step-by-step instructions: 11 items
    • +4Has examples (10 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.

    External checks

    ClawHub: clean
    This is a coherent UPLO cybersecurity knowledge-base connector, but it can access and export sensitive organizational security information.
    LLM: benign (medium) · VirusTotal: · 29 May 2026