CC detecting-mobile-malware-behavior
Detects and analyzes malicious behavior in mobile applications through behavioral analysis, permission abuse detection, network traffic monitoring, and dynamic instrumentation. Use when analyzing suspicious mobile applications for data exfiltration, command-and-control communication, credential stealing, SMS interception, or other malware indicators. Activates for requests involving mobile malware analysis, app behavior monitoring, trojan detection, or suspicious app investigation.
Detects and analyzes malicious behavior in mobile applications through behavioral analysis, permission abuse detection, network traffic monitoring, and…
As a process C 62/100 · Has gaps — weak spots: result and completion, failures and branches, running it twice
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 · 10
✓ No critical or high findings
Medium and low: 10
-
low Risky intent
intent-offensive-securityassets/template.md:1Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Mobile Malware Analysis Report
-
low Risky intent
intent-offensive-securityassets/template.md:25Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| File Encryption | [YES/NO] | Ransomware |
-
low Risky intent
intent-offensive-securityassets/template.md:30Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Domain | [DOMAIN] | C2 Server |
-
low Risky intent
intent-offensive-securityreferences/api-reference.md:10Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)| BIND_DEVICE_ADMIN | CRITICAL | Device lockout, ransomware |
detector -
low Risky intent
intent-offensive-securityreferences/standards.md:19Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Command and Control | T1437.001: Web Protocols | HTTPS beaconing |
-
low Risky intent
intent-offensive-securitySKILL.md:7Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)or other malware indicators. Activates for requests involving mobile malware analysis,
detector -
low Risky intent
intent-offensive-securitySKILL.md:103Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# DEVICE_ADMIN + INTERNET = ransomware capability
-
low Risky intent
intent-offensive-securitySKILL.md:115Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# - Hardcoded C2 server addresses
-
low Risky intent
intent-offensive-securitySKILL.md:212Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| File encryption + ransom note display | Mobile Ransomware |
-
low Risky intent
intent-offensive-securitySKILL.md:224Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| **C2 Beacon** | Regular network check-in from malware to command-and-control server, identifiable by periodic timing patterns |
Files scanned: 8. 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_csf" - note
frontmatter-keyunknown frontmatter key "mitre_attack" - note
frontmatter-keyunknown frontmatter key "mitre_f3"
Process rating: all ten parameters 62/100
- 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
- 30Running it twice. 1 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 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 1834 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
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- -43 reference files, but SKILL.md never points to them: the model will not open them
- -32 of 2 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 486: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 19 items
- +4Has examples (4 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.