CC detecting-fileless-malware-techniques
Detects and analyzes fileless malware that operates entirely in memory using PowerShell, WMI, .NET reflection, registry-resident payloads, and living-off-the-land binaries (LOLBins) without writing traditional executable files to disk. Use for requests involving fileless threat detection, in-memory malware investigation, LOLBin abuse analysis, or WMI persistence examination.
Detects and analyzes fileless malware that operates entirely in memory using PowerShell, WMI, .NET reflection, registry-resident payloads, and…
As a process C 54/100 · Has gaps — References files that are not bundled: references/yara-fileless-powershell.yar
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
- 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 · 10
✓ No critical or high findings
Medium and low: 10
-
medium Dangerous commands
cmd-persistencescripts/agent.py:138Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)r"HKLM\SOFTWARE\Microsoft\Windows\CurrentVersion\Run",
code literal -
medium Dangerous commands
cmd-persistencescripts/agent.py:139Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)r"HKCU\SOFTWARE\Microsoft\Windows\CurrentVersion\Run",
code literal -
low Risky intent
intent-offensive-securitySKILL.md:324Offensive-security / dual-use content (legitimate for authorised testing; review intended use)WMI process creation for lateral movement
-
low Risky intent
intent-offensive-securitySKILL.md:331Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Phase 4 - Privilege Escalation:
-
low Risky intent
intent-offensive-securitySKILL.md:335Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Phase 5 - Lateral Movement:
-
low Risky intent
intent-offensive-securitySKILL.md:379Offensive-security / dual-use content (legitimate for authorised testing; review intended use)7. Map the complete attack chain from initial access through persistence and lateral movement
-
low Risky intent
intent-offensive-securitySKILL.md:390Offensive-security / dual-use content (legitimate for authorised testing; review intended use)FILELESS MALWARE ANALYSIS REPORT
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:403High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)WHERE TargetInstance ISA 'Win3…tem'
detector
A further 2 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/yara-fileless-powershell.yar - note
frontmatter-keyunknown frontmatter key "domain" - note
frontmatter-keyunknown frontmatter key "subdomain" - note
frontmatter-keyunknown frontmatter key "d3fend_techniques" - note
frontmatter-keyunknown frontmatter key "nist_csf" - note
frontmatter-keyunknown frontmatter key "mitre_attack"
Process rating: all ten parameters 54/100
- 0Tools and files. 1 referenced file(s) missing: references/yara-fileless-powershell.yar
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 1 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
- 100Steps. 27 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3933 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 377: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 27 items
- +3Output format is stated explicitly
- +4Has examples (9 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.