CC deobfuscating-javascript-malware
Deobfuscates malicious JavaScript found in phishing pages, web skimmers, and dropper scripts by reversing encoding layers, eval chains, string manipulation, and control-flow obfuscation to reveal the original malicious logic. Use when investigating a phishing page's obfuscated JavaScript, analyzing a Magecart-style web skimmer, or deobfuscating a JavaScript dropper that fetches second-stage malware.
Deobfuscates malicious JavaScript found in phishing pages, web skimmers, and dropper scripts by reversing encoding layers, eval chains, string manipulation…
As a process C 52/100 · Has gaps — References files that are not bundled: [A-Za-z0-9+/=]+
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 · 5
✓ No critical or high findings
Medium and low: 5
-
low Risky intent
intent-offensive-securitySKILL.md:32Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Investigating a phishing page with obfuscated JavaScript that performs credential harvesting or redirect
-
low Dangerous commands
cmd-eval-dynamicSKILL.md:111Dynamic code execution from decoded/untrusted input (documentation of a security skill)- eval(atob("..."))security skill -
low Dangerous commands
cmd-eval-dynamicSKILL.md:112Dynamic code execution from decoded/untrusted input (documentation of a security skill)- eval(unescape("..."))security skill -
low Risky intent
intent-offensive-securitySKILL.md:278Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Keylogger event listeners (onkeypress, oninput)
-
low Risky intent
intent-offensive-securitySKILL.md:308Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **JSDetox**: JavaScript malware analysis tool providing execution emulation and deobfuscation
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+/=]+ - 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+/=]+
- 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 3044 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
- -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 402: 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: 76.