CC generating-threat-intelligence-reports
Generates structured cyber threat intelligence reports at strategic, operational, and tactical levels tailored to specific audiences including executives, security operations teams, and technical analysts. Use when producing finished intelligence products from raw collection data, creating sector threat briefings, or delivering post-incident intelligence assessments. Activates for requests involving CTI report writing, threat briefings, intelligence products, finished intelligence, or executive security reporting.
Generates structured cyber threat intelligence reports at strategic, operational, and tactical levels tailored to specific audiences including executives…
As a process C 62/100 · Has gaps — weak spots: result and completion, 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 · 3
✓ No critical or high findings
Medium and low: 3
-
low Risky intent
intent-offensive-securitySKILL.md:42Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Creating a rapid intelligence assessment in response to a breaking threat (e.g., new zero-day, active ransomware campaign)
-
low Risky intent
intent-offensive-securitySKILL.md:85Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)- Bad: "This report examines threat actor TTPs associated with Cl0p ransomware"
quoted -
low Risky intent
intent-offensive-securitySKILL.md:86Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)- Good: "Cl0p ransomware group is actively exploiting CVE-…353 in Cisco ASA devices to gain initial access; organizations using unpatched ASA appliances face imminent ransomware risk"
quoted
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 "nist_csf" - note
frontmatter-keyunknown frontmatter key "mitre_attack"
Process rating: all ten parameters 62/100
- 0Result and completion. Does not say what the result is
- 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
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 43 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1700 tokens
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
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- -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 519: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 43 items
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.