BB conducting-phishing-incident-response
Respond to phishing incidents by analyzing reported emails, extracting indicators, sandboxing URLs/attachments, assessing credential compromise, quarantining malicious messages organization-wide, and remediating affected accounts. Use when investigating a reported phishing or credential-phishing email, a suspected spearphishing incident, or when a mailbox-wide purge and account remediation is needed.
Respond to phishing incidents by analyzing reported emails, extracting indicators, sandboxing URLs/attachments, assessing credential compromise, quarantining…
As a process B 73/100 · Nearly there — weak spots: failures and branches, 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:67Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Threat intelligence indicates an active phishing campaign targeting the organization
-
low Risky intent
intent-offensive-securitySKILL.md:106Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)- **Confirmed Phishing**: Malicious URL/attachment, spoofed sender, credential harvesting page
detector -
low Risky intent
intent-offensive-securitySKILL.md:118Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Check if the URL redirects to a credential harvesting page
-
low Risky intent
intent-offensive-securitySKILL.md:119Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Identify the phishing kit type (Microsoft 365 login clone, Okta clone, generic)
-
low Risky intent
intent-offensive-securitySKILL.md:205Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| **Credential Harvesting** | Phishing technique that mimics a legitimate login page to capture usernames and passwords |
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "domain" - note
frontmatter-keyunknown frontmatter key "subdomain" - note
frontmatter-keyunknown frontmatter key "mitre_attack" - note
frontmatter-keyunknown frontmatter key "mitre_f3" - note
frontmatter-keyunknown frontmatter key "nist_csf"
Process rating: all ten parameters 73/100
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 50When it triggers. No condition that starts the skill
- 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. 66 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2561 tokens
- 100Running it twice. Mutating operations check current state
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
- -41 reference files, but SKILL.md never points to them: the model will not open them
- -31 of 1 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 403: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 66 items
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.