CB implementing-siem-use-cases-for-detection
Implements SIEM detection use cases by designing correlation rules, threshold alerts, and behavioral analytics mapped to MITRE ATT&CK techniques across Splunk, Elastic, and Sentinel. Use when SOC teams need to expand detection coverage, formalize use case lifecycle management, or build a detection library aligned to organizational threat profile.
Implements SIEM detection use cases by designing correlation rules, threshold alerts, and behavioral analytics mapped to MITRE ATT&CK techniques across…
As a process B 72/100 · Nearly there — weak spots: failures and branches, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
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 · 9
✓ No critical or high findings
Medium and low: 9
-
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:202Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)IEX (IWR 'https://raw.githubusercontent.com/redcanaryco/invoke-atomicredteam/master/inst…ps1' -UseBasicParsing)
security skill -
low Risky intent
intent-offensive-securityreferences/api-reference.md:21Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Test | Validate with Atomic Red Team, measure FP/TP rates |
-
low Risky intent
intent-offensive-securityreferences/api-reference.md:31Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| T1021.002 | SMB/Windows Admin Shares | Lateral Movement |
-
low Risky intent
intent-offensive-securityreferences/api-reference.md:53Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Atomic Red Team: https://github.com/redcanaryco/atomic-red-team
-
low Risky intent
intent-offensive-securitySKILL.md:68Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Testing environment with attack simulation tools (Atomic Red Team, MITRE Caldera)
-
low Risky intent
intent-offensive-securitySKILL.md:122Offensive-security / dual-use content (legitimate for authorised testing; review intended use)name: Credential Dumping via LSASS Access
-
low Risky intent
intent-offensive-securitySKILL.md:198Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)Validate detection rules using Atomic Red Team:
detector -
low Risky intent
intent-offensive-securitySKILL.md:201Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Install Atomic Red Team
-
low Risky intent
intent-offensive-securitySKILL.md:205Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Execute T1003.001 - Credential Dumping
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_ai_rmf" - note
frontmatter-keyunknown frontmatter key "atlas_techniques" - note
frontmatter-keyunknown frontmatter key "d3fend_techniques" - note
frontmatter-keyunknown frontmatter key "nist_csf" - note
frontmatter-keyunknown frontmatter key "mitre_attack" - note
edit-residuethe text marks something as outdated (lines 222, 277): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 72/100
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 2 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 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. 19 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2578 tokens
- 100Progress reporting. Reports progress
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
- -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 348: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 19 items
- +3Output format is stated explicitly
- +4Has examples (12 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.