CC extracting-iocs-from-malware-samples
Extracts indicators of compromise (IOCs) from malware samples, including file hashes, network indicators (IPs, domains, URLs, PCAP indicators), host artifacts (file paths, registry keys, mutexes), and behavioral patterns, using tools like CyberChef, then defangs and exports them in standard threat-intel formats. Use for IOC extraction, threat indicator harvesting, or building detection content from a sample.
Extracts indicators of compromise (IOCs) from malware samples, including file hashes, network indicators (IPs, domains, URLs, PCAP indicators), host artifacts…
As a process C 52/100 · Has gaps — References files that are not bundled: ?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9]
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 · 6
✓ No critical or high findings
Medium and low: 6
-
medium Dangerous commands
cmd-persistenceSKILL.md:383Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)Registry Keys: HKCU\Software\Microsoft\Windows\CurrentVersion\Run\WindowsUpdate
security skill -
low Risky intent
intent-offensive-securitySKILL.md:36Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- A malware analysis (static or dynamic) is complete and actionable indicators need to be extracted for defense teams
-
low Risky intent
intent-offensive-securitySKILL.md:47Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Completed malware analysis report (static analysis, dynamic analysis, or reverse engineering)
-
low Risky intent
intent-offensive-securitySKILL.md:336Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)### Scenario: Building a Comprehensive IOC Package from a Ransomware Sample
detector -
low Risky intent
intent-offensive-securitySKILL.md:338Offensive-security / dual-use content (legitimate for authorised testing; review intended use)**Context**: A ransomware incident requires rapid IOC extraction for blocking across the enterprise while the full investigation continues. Multiple data sources are available: the sample binary, PCAP
-
low Risky intent
intent-offensive-securitySKILL.md:341Offensive-security / dual-use content (legitimate for authorised testing; review intended use)1. Compute all file hashes (MD5, SHA-1, SHA-256, imphash, ssdeep) for the ransomware binary and any dropped files
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: ?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9] - note
frontmatter-keyunknown frontmatter key "domain" - note
frontmatter-keyunknown frontmatter key "subdomain" - note
frontmatter-keyunknown frontmatter key "nist_csf" - note
frontmatter-keyunknown frontmatter key "mitre_attack"
Process rating: all ten parameters 52/100
- 0Tools and files. 1 referenced file(s) missing: ?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9]
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 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 3362 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
- -4Absolute local paths (C:\Users, /home/…): not portable
- -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 411: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 27 items
- +3Output format is stated explicitly
- +4Has examples (7 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.