SKILLEMALL.ai
GitHub ↗ RU Sign in

CC patentmax-disclosure

技术交底书生成。当用户要写技术交底书、专利交底、把研发材料或技术方案整理成交底书、挖专利点、只有一个想法想看看能往哪几个方向申请，或说「帮我写个交底书」「这个能写成专利吗」时使用。Use when the user wants to turn R&D materials or an idea into a patent technical disclosure document (Word). Requires a PatentMax API key.

ClawHub Claude Code author: ip930 v1.0.0 MIT-0 7 files · 1 script body ≈ 974 tokens Open the sourceclawhub.ai↗ analyzed 7 d ago

技术交底书生成。当用户要写技术交底书、专利交底、把研发材料或技术方案整理成交底书、挖专利点、只有一个想法想看看能往哪几个方向申请，或说「帮我写个交底书」「这个能写成专利吗」时使用。Use when the user wants to turn R&D materials or an idea into a…

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

IntegrationWordSoftware developmentData and analyticstype 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
78/100
safety, quality, tests
Safety 60%
70
Quality 40%
91
Run on models
none yet
Process rating
C
57/100
Has gaps
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

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

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 · 6

    ✓ No critical or high findings

    Medium and low: 6
    • medium Exfiltration net-credential-use references/faq.md:73
      Credential used in a network call (verify the destination is the intended service)
      curl -s -H "Authorization: Bearer $PATENTMAX_API_KEY" \
    • medium Exfiltration net-credential-use references/faq.md:77
      Credential used in a network call (verify the destination is the intended service)
      curl -s -H "Authorization: Bearer $PATENTMAX_API_KEY" \
    • medium Exfiltration net-credential-use references/faq.md:81
      Credential used in a network call (verify the destination is the intended service)
      curl -s -H "Authorization: Bearer $PATENTMAX_API_KEY" -o 技术交底书.docx \
    • medium Exfiltration net-credential-use references/faq.md:83
      Credential used in a network call (verify the destination is the intended service)
      curl -s -H "Authorization: Bearer $PATENTMAX_API_KEY" -o 核对说明.docx \
    • medium Exfiltration net-redirectable-api-key scripts/patentmax_disclosure.py:45
      Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
      API key + configurable base URL from environment
    • medium Broad scope meta-broad-allowed-tools SKILL.md:1
      Broad tool permissions pre-approved: Bash
      allowed-tools: Bash Read Write Glob

    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 57/100

    • 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. 3 mutating operations with no state check
    • 70When it triggers. States when to use, but not when not to
    • 100Tools and files. Tools declared in frontmatter
    • 100Steps. 9 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 974 tokens
    • low 10 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)
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +3Description length 228: enough signal without eating the budget
    • +4Structure: 11 headings
    • +3Step-by-step instructions: 9 items
    • +4Has examples (1 code blocks)
    • +4Reference files are cited in the instructions (3 of 3)
    • +3All 1 scripts are documented

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

    External checks

    ClawHub: suspicious
    The skill is a coherent PatentMax helper, but it needs review because it uploads sensitive invention materials with an API key and the script can redirect that traffic to an arbitrary base URL.
    LLM: suspicious (high) · 24 Sept 2026