BD skill-security-scanner
Security scanner for OpenClaw skills. Use when installing, updating, or auditing skills to detect malicious backdoors, suspicious code patterns, data exfiltration risks, and security vulnerabilities. Automatically analyzes Python/JavaScript/Shell code for dangerous functions (eval, exec, system calls), network requests, file operations, environment variable access, obfuscation patterns, and known attack signatures. Provides security score and installation recommendations.
As a process D 39/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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 Risky intent
intent-offensive-securityreferences/rules-reference.md:140Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition; documentation table row)| SUSP…001 | Keylogging | `\b(keyboard\|pynput\|hook\|GetAsyncKeyState\|keylogger)` | Critical |
detectortable -
low Dangerous commands
cmd-privilegereferences/rules-reference.md:177Privilege escalation / world-writable permissions (documentation table row; documentation of a security skill)| PERM001 | Privilege Escalation | `\b(setuid\|setgid\|os\.chmod.*0o[0-7]{3,4}\|777\|sudo)` | High |tablesecurity skill -
low Risky intent
intent-offensive-securityreferences/rules-reference.md:177Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| PERM001 | Privilege Escalation | `\b(setuid\|setgid\|os\.chmod.*0o[0-7]{3,4}\|777\|sudo)` | High | -
low Risky intent
intent-offensive-securitySKILL.md:12Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **System Compromise**: File deletion, permission changes, privilege escalation
-
low Risky intent
intent-offensive-securitySKILL.md:59Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)| SUSP…001 | Keylogger functionality | `pynput`, `keyboard` modules |
detector
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 5. 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 39/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (skill-security-scanner) differs from the folder (skill-security-scanner-clean)
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 100Steps. 40 steps
- 100Execution cost. Instruction body is 1508 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- -215 emoji in the instructions: noise for the model
- -41 reference files, but SKILL.md never points to them: the model will not open them
- -31 of 2 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 476: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 40 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.