BC skill-security-check
Runs VirusTotal-style security checks on OpenClaw/Cursor skills before install, including remote code execution (RCE) and malicious code (obfuscation, exfiltration, backdoors). Use when evaluating a skill from a registry (e.g. ClawHub), before granting OAuth/API credentials, or when the user asks for a security review of a skill.
Runs VirusTotal-style security checks on OpenClaw/Cursor skills before install, including remote code execution (RCE) and malicious code (obfuscation…
As a process C 60/100 · Has gaps — weak spots: inputs and preconditions, consistency, progress reporting
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 · 6
✓ No critical or high findings
Medium and low: 6
-
low Dangerous commands
cmd-pipe-to-shellreference.md:36Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation table row; documentation of a security skill)| **Remote code execution (RCE)** | Do **not** instruct the agent to: run `curl … \| sh` or `wget … \| bash`; use `eval` on remote or user-supplied input; build shell commands from unvalidated strings
tablesecurity skill -
low Dangerous commands
cmd-pipe-to-shellreference.md:110Downloads and executes remote code from an unrecognised host (pipe to shell) (negated — the text forbids it)- [ ] **RCE:** No `curl|sh`, `wget|bash`, eval of remote input, or unvalidated command construction; no privileged (root/sudo) execution of remote or dynamic code
negated
A further 4 matches are quotations in this security skill's documentation and are not counted as findings.
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 60/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (skill-security-check) differs from the folder (skill-safety-checker)
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 60Failures and branches. 2 branches
- 70When it triggers. States when to use, but not when not to
- 85Steps. 67 steps, 1 vague phrases
- 100Execution cost. Instruction body is 3266 tokens
- 100Running it twice. Mutating operations check current state
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)
- +4No input/output examples
- -214 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 331: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 67 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.