SKILLEMALL.ai
GitHub ↗ RU Sign in

BD zt4ai-self-audit

Zero Trust security audit for AI agent workspaces, skills, and configurations. Based on Microsoft's Zero Trust for AI (ZT4AI) framework and the "Caging the Agents" research (arXiv:2603.17419). Audits installed skills for prompt injection risk, credential exposure, excessive privilege, behavioral manipulation, and integrity drift. Use when: performing a security audit of agent skills, reviewing newly installed skills from ClawHub or other sources, checking for prompt injection vectors in workspace files, auditing agent permissions and trust boundaries, verifying skill file integrity against a baseline, or hardening an agent's security posture. Triggers on: "audit my skills", "security check", "ZT4AI", "zero trust audit", "check skill integrity", "am I secure", "harden my agent", "review my trust boundaries".

ClawHub Agent Skills author: tanarchytan v1.0.0 MIT-0 7 files · 1 script body ≈ 1 390 tokens Open the sourceclawhub.ai↗ analyzed 12 d ago

Zero Trust security audit for AI agent workspaces, skills, and configurations.

As a process D 49/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches

AnalyzerAI 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
B
94/100
safety, quality, tests
Safety 60%
98
Quality 40%
87
Run on models
none yet
Process rating
D
49/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
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 references/audit-checklist.md:41
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - [ ] **No privilege escalation**: Does the skill avoid requesting elevated privileges unnecessarily?
    • low Risky intent intent-offensive-security SKILL.md:32
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      3. **OWASP Agentic AI Top 10** — Trust boundary violations, privilege escalation, resource exhaustion

    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 49/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 1 mutating operations with no state check
    • 60Tools and files. Uses tools (web) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 100Steps. 35 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1390 tokens
    • low The response is described with custom markup (4 tags): a typed call is more reliable

    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

    • +4Description does not say when NOT to use the skill (false activations)
    • +3Description length 818: 120–800 characters recommended
    • +3Output format is not stated: the model decides each time
    • -31 of 1 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 8 example trigger phrases
    • +4Structure: 13 headings
    • +3Step-by-step instructions: 35 items
    • +4Has examples (5 code blocks)
    • +4Reference files are cited in the instructions (4 of 4)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.

    External checks

    ClawHub: suspicious
    This security-audit skill is coherent, but it should be reviewed because it can broadly inspect private workspace files and save persistent audit data without tight scoping or explicit approval.
    LLM: suspicious (high) · VirusTotal: · 14 Sept 2026