AD hunt-tls-network
Hunt TLS/SSL and DNS misconfigurations — missing HSTS (downgrade attack), weak cipher suites, expired/invalid certificates, mTLS bypass, missing SPF/DKIM/DMARC (email spoofing), DNS Zone Transfer (AXFR), dangling CNAME subdomain takeover, CAA records. Most of these are Info/Low on their own — this skill is opinionated about which findings actually pay (spoofable DMARC with delivered-to-inbox proof, AXFR returning internal hosts, dangling-CNAME takeover) versus which get rejected as best-practice noise (missing CAA, missing HSTS with no MitM position). Use during recon to find infrastructure weaknesses, and to TRIAGE them honestly before reporting.
Hunt TLS/SSL and DNS misconfigurations — missing HSTS (downgrade attack), weak cipher suites, expired/invalid certificates, mTLS bypass, missing…
As a process D 43/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Risky intent
intent-offensive-securitySKILL.md:56Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **SWEET32 (CVE-…183)** — 3DES birthday attack. Requires a long-lived TLS session, an on-path attacker, and ~hundreds of GB / hours of same-key traffic. Realistically un-demonstrable in a bug bo
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "report_count" - note
frontmatter-keyunknown frontmatter key "sources"
Process rating: all ten parameters 43/100
- 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
- 30Running it twice. 4 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Execution cost. Instruction body is 4863 tokens
- 85Steps. 37 steps, 2 vague phrases
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 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
- +1No license
- +2Single-language instructions
- +3Description length 655: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 37 items
- +4Has examples (11 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.