BD IaC Sec Audit
Infrastructure as Code security auditor for Terraform (.tf), CloudFormation (YAML/JSON), and Pulumi (TypeScript/Python). Detects 12 high-impact cloud misconfigurations — public S3 buckets, security groups open to 0.0.0.0/0 on SSH/RDP, unencrypted EBS/RDS/S3, wildcard IAM policies, hardcoded credentials, missing deletion protection, public RDS, unrestricted Lambda execution roles, and more. Zero external dependencies (no tfsec/checkov required). Works on any .tf or CloudFormation file. CI fail-gate included.
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 · 3
✓ No critical or high findings
Medium and low: 3
-
low Risky intent
intent-offensive-securitySKILL.md:79Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)Finds IAM policies with `"Action": ["*"]` or `"Resource": ["*"]`. Over-permissive IAM is the #1 privilege escalation path in cloud environments. A compromised service with `*` on `*` = full account ta
detector -
low Risky intent
intent-offensive-securitySKILL.md:97Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Finds `aws_…ket` without `aws_…ing` enabled. Versioning is the cheapest protection against accidental deletion and ransomware overwrite attacks.
-
low Secrets in code
secret-password-literalSKILL.md:117Hard-coded password / key literal (may be an example)Hardcoded AWS secret: password = "prod…024"
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 ≈ 9172 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 40Consistency. Frontmatter name (IaC Sec Audit) differs from the folder (phy-iac-sec-audit)
- 40Execution cost. Instruction body is 9172 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (git) that frontmatter does not declare
- 100Steps. 10 steps
- 100Progress reporting. Reports progress
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 512: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 10 items
- +4Has examples (4 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 57.