AF openclaw-security-auditor
OpenClaw Security Auditor (OSA) - Comprehensive security auditing tool for OpenClaw deployments. Provides 60-second security diagnosis, risk scoring (0-100), bilingual reports (Chinese/English), and automated fix suggestions. Use when users request security audits, vulnerability scanning, configuration validation, or security hardening for their OpenClaw installations.
As a process F 38/100 · Will not run — References files that are not bundled: scripts/i18n.py, scripts/scan_current.py, scripts/fix_security.py
How to improve
- 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
-
low Risky intent
intent-offensive-securitySKILL.md:177Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Does not perform network penetration testing
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: scripts/i18n.py - warning
missing-refreference to a missing file: scripts/scan_current.py - warning
missing-refreference to a missing file: scripts/fix_security.py - warning
missing-refreference to a missing file: scripts/debug_session.py - warning
missing-refreference to a missing file: references/vulnerability-db.md - warning
missing-refreference to a missing file: references/api-reference.md - warning
missing-refreference to a missing file: references/integration-guide.md
Process rating: all ten parameters 38/100
- 0Tools and files. 7 referenced file(s) missing: scripts/i18n.py, scripts/scan_current.py, scripts/fix_security.py
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (openclaw-security-auditor) differs from the folder (openclaw-security-auditor-skill)
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 72 steps
- 100Execution cost. Instruction body is 1727 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 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)
- +2Single-language instructions
- +3Description length 371: enough signal without eating the budget
- +4Structure: 35 headings
- +3Step-by-step instructions: 72 items
- +3Output format is stated explicitly
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 3 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.