BF freechat-deepseek
openclaw browser open https://chat.deepseek.com and login it, then input questions from user's messages, extract response of deepseek chat to reply user.
As a process F 54/100 · Will not run — References files that are not bundled: chrome-remote-debugging.png
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 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
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bash(curl:*)allowed-tools: Bash(npm:*) Bash(npx:*) Bash(openclaw:*) Bash(curl:*) Read Write WebFetch Browser
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 15745 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: chrome-remote-debugging.png - note
frontmatter-keyunknown frontmatter key "alias"
Process rating: all ten parameters 54/100
- 0Tools and files. 1 referenced file(s) missing: chrome-remote-debugging.png
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 12 mutating operations with no state check
- 40Execution cost. Instruction body is 15745 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 77 steps
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 27 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (12 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
- -4Absolute local paths (C:\Users, /home/…): not portable
- -240 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 153: enough signal without eating the budget
- +4Structure: 73 headings
- +3Step-by-step instructions: 77 items
- +3Output format is stated explicitly
- +4Has examples (47 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.