AB security-incident-response
Run or document a security incident response — contain, eradicate, recover, and learn. Use when responding to a breach/compromise/security incident, writing an IR plan or runbook, or producing a post-incident report. Produces a phase-by-phase response (triage, contain, eradicate, recover, post-incident) with the immediate actions, comms, evidence-handling, and a blameless review. For incidents on systems you own or defend.
Run or document a security incident response — contain, eradicate, recover, and learn.
As a process B 69/100 · Nearly there — weak spots: when it triggers, failures and branches, running it twice
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:17Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)- **What's happening** — the observed incident (malware, unauthorized access, data exfiltration, ransomware, account compromise), and how it was detected.
quoted
Files scanned: 1. 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 69/100
- 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
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 21 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 888 tokens
- 100Progress reporting. Reports progress
- 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)
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 426: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 21 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.