DC patentmax-patent-search
全球专利检索与统计分析。当用户提到专利检索、找专利、现有技术、相似专利、引证分析、某家公司有多少专利、某个领域谁在申请、技术趋势分布，或直接给出一个专利号、公开号时使用。Use when the user asks to search patents, look up a patent, find similar patents, analyse citations, or profile a company patent portfolio. Requires a PatentMax API key.
全球专利检索与统计分析。当用户提到专利检索、找专利、现有技术、相似专利、引证分析、某家公司有多少专利、某个领域谁在申请、技术趋势分布，或直接给出一个专利号、公开号时使用。Use when the user asks to search patents, look up a patent, find similar…
As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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".
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.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- 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 · 7
✓ No critical or high findings
Medium and low: 7
-
medium Exfiltration
net-credential-useINSTALL.md:77Credential used in a network call (verify the destination is the intended service)curl -s -H "Authorization: Bearer $PATENTMAX_API_KEY" \
-
medium Exfiltration
net-credential-usereferences/api-reference.md:15Credential used in a network call (verify the destination is the intended service)curl -s -H "Authorization: Bearer $PATENTMAX_API_KEY" \
-
medium Exfiltration
net-credential-usereferences/api-reference.md:57Credential used in a network call (verify the destination is the intended service)curl -s -H "Authorization: Bearer $PATENTMAX_API_KEY" \
-
medium Exfiltration
net-credential-usereferences/api-reference.md:75Credential used in a network call (verify the destination is the intended service)curl -s -H "Authorization: Bearer $PATENTMAX_API_KEY" \
-
medium Exfiltration
net-credential-usereferences/api-reference.md:100Credential used in a network call (verify the destination is the intended service)curl -s -H "Authorization: Bearer $PATENTMAX_API_KEY" \
-
medium Exfiltration
net-redirectable-api-keyscripts/patentmax_client.py:49Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Bash Read Write WebFetch
Files scanned: 12. 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 58/100
- 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
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 4669 tokens
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 52 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. No mutating operations
- low 18 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
- +2Single-language instructions
- +3Description length 254: enough signal without eating the budget
- +4Structure: 36 headings
- +3Step-by-step instructions: 52 items
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (6 of 6)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.