BD K8s Security Audit
Kubernetes manifest security auditor (CIS Kubernetes Benchmark). Scans all YAML/JSON manifests in your repository for privileged containers, hostNetwork/hostPID/hostIPC, dangerous hostPath mounts, missing resource limits/probes, latest image tags, RBAC over-permission (cluster-admin bindings, wildcard verbs), secrets in env vars, missing NetworkPolicy, missing seccomp/AppArmor profiles. Maps findings to CIS Benchmark controls and PSS (Pod Security Standards). Zero dependencies beyond PyYAML. Zero competitors on ClawHub.
As a process D 37/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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-securitySKILL.md:83Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| **Restricted** | All of Baseline + non-root, no privilege escalation, seccomp, drop ALL caps |
-
low Risky intent
intent-offensive-securitySKILL.md:168Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Privilege escalation
-
low Risky intent
intent-offensive-securitySKILL.md:170Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)add("C002", HIGH, "Privilege escalation allowed",detector -
low Risky intent
intent-offensive-securitySKILL.md:360Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)f"Allows {verbs & SECRET_VERBS} on secrets — enables credential harvesting.",detector
A further 2 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
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 6943 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 37/100
- 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. 4 mutating operations with no state check
- 40Consistency. Frontmatter name (K8s Security Audit) differs from the folder (phy-k8s-security-audit)
- 60Tools and files. Uses tools (node) that frontmatter does not declare
- 70Execution cost. Instruction body is 6943 tokens
- 100Steps. 6 steps
- low 10 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)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 525: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 6 items
- +4Has examples (7 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 57.