SKILLEMALL.ai

BB web-test

Тестирование 1С через веб-клиент — автоматизация действий в браузере. Используй когда пользователь просит проверить, протестировать, автоматизировать действия в 1С через браузер

Nikolay-Shirokov/cc-1c-skills Claude Code author: Nikolay-Shirokov MIT 69 files body ≈ 8 360 tokens Open the sourcegithub.com analyzed 2 d ago

Тестирование 1С через веб-клиент — автоматизация действий в браузере.

As a process B 76/100 · Nearly there — weak spots: inputs and preconditions, execution cost

Procedure1CData and analyticstype and topics are labelled automatically from the skill text
JSON
Technical rating
B
75/100
safety, quality, tests
Safety 60%
83
Quality 40%
62
Run on models
none yet
Process rating
B
76/100
Nearly there
Inputs and preconditions w 11
0
Execution cost w 6
40
Result and completion w 14
60
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.

Obfuscation 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 files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.

For the author

Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.

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

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 5

✓ No critical or high findings

Medium and low: 5
  • medium Obfuscation uni-mixed-script-word scripts/dom/_shared.mjs:150
    Word mixing Latin and Cyrillic letters (homoglyph obfuscation) (2 occurrences)
    * "(checkbox)" (subTarget:checkbox) + "КолонкаN" (subTarget:title). Data columns are numbered
  • medium Exfiltration intent-browser-credential-store scripts/engine/core/session.mjs:572
    Accesses a browser credential / cookie store (code comment)
    * cookies() is served by the browser process (measured: 1ms against a wedged renderer),
    comment
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Bash Read Write Glob Grep
  • low Secrets in code secret-high-entropy-token scripts/dom/forms.mjs:23
    High-entropy token-like string (may be an id, hash or a credential)
    *   list open        → cross VW_p…ton
  • low Secrets in code secret-high-entropy-token scripts/package-lock.json:17
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…uWm+fFRcIOgKBMiOBP+eXiy…9ab+DDKA==",
    detector

Files scanned: 68. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 8360 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 76/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 40Execution cost. Instruction body is 8360 tokens: crowds the task out of the window
  • 60Result and completion. Output format stated, no completion criterion
  • 70When it triggers. States when to use, but not when not to
  • 100Tools and files. Tools declared in frontmatter
  • 100Steps. 39 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 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

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)
  • -2localhost URLs: will not work for another user
  • -31 of 3 scripts are never mentioned in SKILL.md
  • +1No license
  • +3Description length 177: enough signal without eating the budget
  • +4Structure: 57 headings
  • +3Step-by-step instructions: 39 items
  • +3Output format is stated explicitly
  • +4Has examples (39 code blocks)
  • +2Bilingual instructions (RU + EN)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 62.