AB security-threat-model
Write a STRIDE-based threat model for a service or feature. Use when asked to produce a threat model, document security risks, identify attack vectors, assess a service's security posture, or prepare for a security design review. Produces a structured threat model covering assets, trust boundaries, STRIDE threat enumeration per component, risk scores, mitigation controls, and residual risk sign-off.
Write a STRIDE-based threat model for a service or feature.
As a process B 71/100 · Nearly there — weak spots: 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:160Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| T-016 | T | Privilege escalation via DB account with excessive permissions | App uses a superuser DB account | [e.g. Least-privilege DB role per service / none] |
-
low Risky intent
intent-offensive-securitySKILL.md:183Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| T-007 | Privilege escalation via missing role check | 3 | 5 | 15 | High | [Open / Mitigated / Accepted] |
-
low Risky intent
intent-offensive-securitySKILL.md:198Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| T-007 | Privilege escalation | Add RBAC middleware to all `/admin/*` routes; write integration test for role boundary | [Engineer name] | [Date] | [JIRA-124] |
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "deprecated" - note
frontmatter-keyunknown frontmatter key "supersededBy"
Process rating: all ten parameters 71/100
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 4 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 32 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3652 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
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)
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +3Description length 402: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 32 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.