BB designing-adversary-engagement-with-mitre-engage
Plan, run, and measure an adversary engagement operation using the MITRE Engage framework so that deployed deception is driven by strategy instead of deployed ad hoc. Covers the Engage Matrix (Prepare, Expose, Affect, Elicit, Understand), the 10-Step Operational Process, mapping engagement Activities to the ATT&CK techniques they expose, and defining measurable Goals and Operational Objectives. Use when a team has honeypots, honeytokens, or canary tokens but no coordinating strategy, when leadership asks "should we engage attackers and how", when building a deception/denial program, when writing an adversary engagement operation plan, or when deciding which deception Activities to deploy against a specific threat actor. Keywords: MITRE Engage, adversary engagement, cyber deception strategy, denial and deception, Engage Matrix, EAC, EGO, Expose Affect Elicit, deception program, honeypot strategy, engagement operation.
Plan, run, and measure an adversary engagement operation using the MITRE Engage framework so that deployed deception is driven by strategy instead of deployed…
As a process B 67/100 · 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-securityassets/template.md:28Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| T1083 | Enumerates files | Decoy Content, Pocket Litter | [Blue team] | deploying-decoy-files-for-ransomware-detection |
Files scanned: 5. 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" - note
edit-residuethe text marks something as outdated (lines 36, 105): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 67/100
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 13 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. 33 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2597 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 930: 120–800 characters recommended
- +4No input/output examples
- +2Single-language instructions
- +4Structure: 18 headings
- +3Step-by-step instructions: 33 items
- +3Output format is stated explicitly
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.