SKILLEMALL.ai
GitHub ↗ RU Sign in

AC public-legal-ai-endpoint-protection

Reviews public or shared AI-backed web endpoints for abuse, excessive cost, data exposure, unsafe browser control, weak request limits, and missing human approval. Use before launching or materially changing an HTTP or API endpoint that can invoke an AI model. Do not use as a penetration test, compliance certification, or substitute for runtime monitoring and professional security review.

lawve-ai/awesome-legal-skills Agent Skills author: lawve-ai 3 files body ≈ 895 tokens Open the sourcegithub.com↗ analyzed 63 min ago

Reviews public or shared AI-backed web endpoints for abuse, excessive cost, data exposure, unsafe browser control, weak request limits, and missing human…

As a process C 63/100 · Has gaps — weak spots: inputs and preconditions, consistency, running it twice

AnalyzerInfrastructureSecuritytype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
A
95/100
safety, quality, tests
Safety 60%
98
Quality 40%
91
Run on models
none yet
Process rating
C
63/100
Has gaps
Inputs and preconditions w 11
0
Progress reporting w 2
0
Running it twice w 4
30
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 README.md:25
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      This Skill is a preventive design review. It is not a penetration test, compliance certification, incident-response service, or guarantee of security.
    • low Risky intent intent-offensive-security SKILL.md:3
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      description: Reviews public or shared AI-backed web endpoints for abuse, excessive cost, data exposure, unsafe browser control, weak request limits, and missing human approval. Use before launching or

    Files scanned: 3. 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 63/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 1 mutating operations with no state check
    • 40Consistency. Frontmatter name (public-legal-ai-endpoint-protection) differs from the folder (public-legal-ai-endpoint-protection-adrian-lerer)
    • 50When it triggers. No condition that starts the skill
    • 50Failures and branches. 0 branches, has a failure section
    • 60Result and completion. Output format stated, no completion criterion
    • 100Tools and files. No external tools needed
    • 100Steps. 25 steps
    • 100Execution cost. Instruction body is 895 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
    • +1No license
    • +2Single-language instructions
    • +4Description says when NOT to use the skill
    • +3Description length 391: enough signal without eating the budget
    • +4Structure: 8 headings
    • +3Step-by-step instructions: 25 items
    • +3Output format is stated explicitly
    • +4Has examples (1 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.