AB soc-alert-triage
Use when a SOC, MDR, or incident-response analyst needs to triage a single security alert from a SIEM, EDR, XDR, or detection pipeline. Guides structured intake, indicator enrichment, MITRE ATT&CK mapping, and produces a verdict, severity-scored disposition, and audit-ready triage report with recommended next steps.
As a process B 79/100 · Nearly there — weak spots: when it triggers, running it twice, progress reporting
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 · 5
✓ No critical or high findings
Medium and low: 5
-
low Risky intent
intent-offensive-securitySKILL.md:49Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)- **Identity / Authentication** — suspicious logon, impossible travel, MFA fatigue, password spray, privilege escalation
detector -
low Risky intent
intent-offensive-securitySKILL.md:50Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)- **Endpoint / Malware** — malicious process execution, ransomware behavior, LOLBin abuse, persistence mechanism
detector -
low Risky intent
intent-offensive-securitySKILL.md:51Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)- **Network** — beaconing, C2 callback, port scan, lateral movement, unusual egress
detector -
low Risky intent
intent-offensive-securitySKILL.md:86Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Outbound connection to rare domain | Command and Control | T1071.001 | DNS lookup in alert payload |
-
low Risky intent
intent-offensive-securitySKILL.md:118Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| **Critical** | Active exploitation of a crown-jewel asset, confirmed data theft, ransomware execution, or domain-wide compromise |
Files scanned: 4. 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 79/100
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Failures and branches. 9 branches
- 100Tools and files. No external tools needed
- 100Steps. 41 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2568 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)
- +1No license
- +2Single-language instructions
- +3Description length 317: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 41 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.