CD ai-security
Use when assessing an AI/ML system or LLM agent for prompt injection, jailbreaks, model inversion, data poisoning or tool abuse. Maps findings to MITRE ATLAS and scores robustness with ai_threat_scanner.py.
Maps findings to MITRE ATLAS and scores robustness with aithreatscanner.py.
As a process D 47/100 · Unfinished process — References files that are not bundled: ../threat-detection/SKILL.md, ../incident-response/SKILL.md, ../cloud-security/SKILL.md
How to improve
- The text references files that are not there: add them or drop the references.
- 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 · 12
✓ No critical or high findings
Medium and low: 12
-
low Risky intent
intent-offensive-securityreferences/atlas-coverage.md:68Offensive-security / dual-use content (legitimate for authorised testing; review intended use)2. Jailbreak template database with regular updates from red team findings
-
low Risky intent
intent-offensive-securitySKILL.md:213Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Privilege escalation via tools | Agent uses tools to access resources outside scope | AML.T0051 | Resource access scope monitoring |
-
low Risky intent
intent-offensive-securitySKILL.md:348Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)2. **Treating static signature matching as complete** — Injection signature matching catches known patterns. Novel injection techniques that don't match existing signatures will not be detected. Compl
detector
A further 9 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../threat-detection/SKILL.md - warning
missing-refreference to a missing file: ../incident-response/SKILL.md - warning
missing-refreference to a missing file: ../cloud-security/SKILL.md - warning
missing-refreference to a missing file: ../security-pen-testing/SKILL.md
Process rating: all ten parameters 47/100
- 0Tools and files. 4 referenced file(s) missing: ../threat-detection/SKILL.md, ../incident-response/SKILL.md, ../cloud-security/SKILL.md
- 0Failures and branches. Linear process with no failure handling
- 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
- 70Execution cost. Instruction body is 4395 tokens
- 85Steps. 57 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 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)
- +1No license
- +2Single-language instructions
- +3Description length 206: enough signal without eating the budget
- +4Structure: 37 headings
- +3Step-by-step instructions: 57 items
- +3Output format is stated explicitly
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.