AB brand-impersonation-response
Respond to a brand or executive impersonation incident — deepfaked executives, cloned support lines, fake apps, spoofed domains, or AI-generated scam content wearing your name. Use when a deepfake of a leader is circulating, customers report a fake version of your product or support channel, or to prepare the impersonation playbook before it happens. Produces an incident response: verification protocol, takedown sequencing by platform, customer and public communications, and the hardening plan. For general crisis comms use press-release/pm-crisis skills; for security incidents inside your systems use security-incident-response.
Respond to a brand or executive impersonation incident — deepfaked executives, cloned support lines, fake apps, spoofed domains, or AI-generated scam content…
As a process B 74/100 · Nearly there — weak spots: when it triggers, 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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Risky intent
intent-offensive-securitySKILL.md:26Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **The harm mechanism**: financial scam? credential harvesting? reputation/market manipulation? (Drives urgency and legal posture)
-
low Risky intent
intent-offensive-securitySKILL.md:37Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **Payment/credential harvesting first**: hosting provider + registrar (impersonation/phishing abuse reports), Google Safe Browsing / Microsoft SmartScreen flagging (kills most browser traffic faster
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 74/100
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 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. 27 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1440 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- high The skill tells the model to perform an irreversible action with no human approval
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 635: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 27 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.