CB browser-vm-setup
Run a browser-driving agent on a Linux VM — Xvfb, Chromium launch traps, egress cost tiers. Use when headless fails on your VM or Chromium dies on launch. Stops at any bot defence.
Run a browser-driving agent on a Linux VM — Xvfb, Chromium launch traps, egress cost tiers.
As a process B 65/100 · Nearly there — weak spots: when it triggers, running it twice
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 contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
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 · 8
✓ No critical or high findings
Medium and low: 8
-
medium Dangerous commands
cmd-persistenceSKILL.md:195Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)( crontab -l 2>/dev/null | grep -q openclaw-purge ) || \
security skill -
medium Dangerous commands
cmd-persistenceSKILL.md:196Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)( crontab -l 2>/dev/null; \
security skill -
medium Dangerous commands
cmd-persistenceSKILL.md:198Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)) | crontab -
security skill -
low Dangerous commands
cmd-privilegeSKILL.md:188Privilege escalation / world-writable permissions (documentation of a security skill)# it before running. Piping a remote script into sudo bash is the operator's call.
security skill -
low Dangerous commands
cmd-cron-mentionSKILL.md:195Mentions editing / listing crontab (documentation of a security skill)( crontab -l 2>/dev/null | grep -q openclaw-purge ) || \
security skill -
low Dangerous commands
cmd-cron-mentionSKILL.md:196Mentions editing / listing crontab (documentation of a security skill)( crontab -l 2>/dev/null; \
security skill -
low Dangerous commands
cmd-cron-mentionSKILL.md:201Mentions editing / listing crontab (documentation of a security skill)crontab -l | grep -c openclaw-purge # Output: 1
security skill -
low Dangerous commands
cmd-cron-mentionSKILL.md:259Mentions editing / listing crontab (documentation table row; documentation of a security skill)| Files older than the retention window still on disk | cron never installed, or `crontab -l` was never checked | re-run the §8 block **including the verify and the probe** |
tablesecurity skill
Files scanned: 2. 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 65/100
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 6 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4720 tokens
- 100Steps. 8 steps
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 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
- +1No license
- +2Single-language instructions
- +3Description length 180: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 8 items
- +3Output format is stated explicitly
- +4Has examples (9 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.