DD house-hunter
对话式找房 — 房产中介 skill，面向年轻租客，多源数据融合（地图/小红书/链家/新闻）。
对话式找房 — 房产中介 skill，面向年轻租客，多源数据融合（地图/小红书/链家/新闻）。
As a process D 39/100 · Unfinished process — References files that are not bundled: scripts/reports/templates/search.md.j2, scripts/reports/templates/deep_dive.md.j2
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
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
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- 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 · 3
-
high Exfiltration
intent-browser-credential-storeextension/background.js:231Accesses a browser credential / cookie storeconst cookies = await chrome.cookies?.getAll({ domain: d.host });
Medium and low: 2
-
medium Exfiltration
net-redirectable-api-keyscripts/_common.py:51Helper 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 AskUserQuestion WebFetch WebSearch
Files scanned: 64. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 5695 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: scripts/reports/templates/search.md.j2 - warning
missing-refreference to a missing file: scripts/reports/templates/deep_dive.md.j2 - note
edit-residuethe text marks something as outdated (lines 312): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 39/100
- 0Tools and files. 2 referenced file(s) missing: scripts/reports/templates/search.md.j2, scripts/reports/templates/deep_dive.md.j2
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 70Execution cost. Instruction body is 5695 tokens
- 100Steps. 97 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. No mutating operations
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 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)
- +3Description length 47: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- -2localhost URLs: will not work for another user
- -250 emoji in the instructions: noise for the model
- -31 of 8 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +4Structure: 59 headings
- +3Step-by-step instructions: 97 items
- +4Has examples (27 code blocks)
- +4Reference files are cited in the instructions (1 of 6)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 43.