CC unbroker
Remove your info from data-broker sites, by name or phone.
Remove your info from data-broker sites, by name or phone.
As a process C 59/100 · Has gaps — weak spots: result and completion, when it triggers
The same skill appears in 1 more place: hermes-agent
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Dangerous commands
cmd-background-processscripts/cdp.py:141Starts a background / autostarted process (string literal in code, not executed)avoids referencing os.setsid, so there is no Windows import-time footgun); Windows uses
code literal
Files scanned: 55. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6978 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "prerequisites"
Process rating: all ten parameters 59/100
- 0Result and completion. Does not say what the result is
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 60Consistency. The Hermes dialect needs category and tags
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 6978 tokens
- 85Steps. 48 steps, 2 vague phrases
- 100Failures and branches. 2 branches, has a failure section
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (37 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
- +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 58: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -318 of 19 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +4Structure: 11 headings
- +3Step-by-step instructions: 48 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (2 of 3)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.
In the sandbox The scripts kept to themselves
The skill's scripts were run in a throwaway machine: no network, fake keys in the home directory, a tracer watching. We wrote down what they did. Reaching for the network or for secrets caps the technical grade at C; a quiet run adds no points.
Запущено 12 скриптов, ещё 7 не поместились в лимит; каждому дали двадцать секунд, поддельный домашний каталог с ключами и сеть, в которой ничего нет.
scripts/autopilot.py | ничего за пределами своей папки |
scripts/badbool.py | ничего за пределами своей папки |
scripts/brokers.py | ничего за пределами своей папки |
scripts/cdp.py | ничего за пределами своей папки |
scripts/config.py | ничего за пределами своей папки |
scripts/crypto.py | ничего за пределами своей папки |
scripts/dossier.py | ничего за пределами своей папки |
scripts/email_modes.py | ничего за пределами своей папки |
scripts/emailer.py | ничего за пределами своей папки |
scripts/ledger.py | ничего за пределами своей папки |
scripts/legal.py | ничего за пределами своей папки |
scripts/paths.py | ничего за пределами своей папки |
11 Oct 2026