BC skill-scanner
Scan installed OpenClaw skills for malicious code patterns including ClickFix social engineering, reverse shell (RAT), and data exfiltration. Uses OG-Text model for agentic detection.
Scan installed OpenClaw skills for malicious code patterns including ClickFix social engineering, reverse shell (RAT), and data exfiltration.
As a process C 51/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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 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".
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.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 9
✓ No critical or high findings
Medium and low: 9
-
medium Exfiltration
exfil-read-secret-filesSKILL.md:320Reads credential / secret files (documentation of a security skill)const keys = fs.readFileSync(path.join(os.homedir(), '.ssh/id_rsa'), 'utf8');
security skill -
low Risky intent
intent-offensive-securitySKILL.md:3Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)description: Scan installed OpenClaw skills for malicious code patterns including ClickFix social engineering, reverse shell (RAT), and data exfiltration. Uses OG-Text model for agentic detection.
detector -
low Risky intent
intent-offensive-securitySKILL.md:130Offensive-security / dual-use content (legitimate for authorised testing; review intended use)### 2. RAT (Remote Access Trojan / Reverse Shell)
-
low Risky intent
intent-offensive-securitySKILL.md:132Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Reverse shell connections (bash -i >& /dev/tcp/, nc -e, python socket connect-back)
-
low Risky intent
intent-offensive-securitySKILL.md:194Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)If the response is not valid JSON, try to extract JSON from markdown code fences. If parsing still fails and the response text contains words like "malicious", "suspicious", "backdoor", "reverse shell
detector -
low Risky intent
intent-offensive-securitySKILL.md:265Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Critical | Active exfiltration, reverse shell, or confirmed malicious payload |
A further 3 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 51/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 5 mutating operations with no state check
- 40Consistency. Frontmatter name (skill-scanner) differs from the folder (antivirus)
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 70When it triggers. States when to use, but not when not to
- 100Steps. 49 steps
- 100Execution cost. Instruction body is 3140 tokens
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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 183: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 49 items
- +4Has examples (11 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.