BC active-directory-attacks
Assess Active Directory attack paths using scoped configuration review and controlled synthetic lab validation; identify prerequisites, evidence and mitigations.
Assess Active Directory attack paths using scoped configuration review and controlled synthetic lab validation; identify prerequisites, evidence and…
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, failures and branches
The same skill appears in 2 more places: agentic-awesome-skills, agentic-awesome-skills
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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Risky intent
intent-offensive-securityreferences/advanced-attacks.md:47Offensive-security / dual-use content (legitimate for authorised testing; review intended use)For every candidate write down observed preconditions, one minimal synthetic test, safe baseline, explicit stop condition, pre-state and cleanup verification. A failed test does not justify privilege
-
low Risky intent
intent-offensive-securitySKILL.md:30Offensive-security / dual-use content (legitimate for authorised testing; review intended use)For explicitly authorized AD security assessments or isolated training labs. Start with supplied configuration and owner evidence, then choose the smallest permitted validation. This document does not
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "risk" - note
frontmatter-keyunknown frontmatter key "source" - note
frontmatter-keyunknown frontmatter key "date_added" - note
edit-residuethe text marks something as outdated (lines 50): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 51/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 5 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1594 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 161: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 5 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.