CD malware-analyst
Expert malware analyst specializing in defensive malware research, threat intelligence, and incident response. Masters sandbox analysis, behavioral analysis, and malware family identification. Handles static/dynamic analysis, unpacking, and IOC extraction. Use PROACTIVELY for malware triage, threat hunting, incident response, or security research.
Expert malware analyst specializing in defensive malware research, threat intelligence, and incident response.
As a process D 45/100 · Unfinished process — weak spots: when it triggers, inputs and preconditions, failures and branches
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 · 6
✓ No critical or high findings
Medium and low: 6
-
medium Dangerous commands
cmd-persistenceSKILL.md:79Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)Registry Run keys - HKCU/HKLM\Software\Microsoft\Windows\CurrentVersion\Run
security skill -
medium Dangerous commands
cmd-persistenceSKILL.md:85Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)Startup folder - %APPDATA%\Microsoft\Windows\Start Menu\Programs\Startup
security skill -
low Risky intent
intent-offensive-securityskill-card.md:3Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Provides defensive malware analysis guidance for triage, static and dynamic analysis, unpacking, IOC extraction, and incident-response reporting.
-
low Risky intent
intent-offensive-securityskill-card.md:17Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)Security analysts, incident responders, and threat researchers use this skill for authorized malware triage, static and dynamic analysis planning, IOC extraction, and report preparation. It should be
detector -
low Risky intent
intent-offensive-securityskill-card.md:27Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Mitigation: Use only for authorized defensive malware analysis in a dedicated, revertible sandbox or isolated VM with controlled networking and no shared host folders or credentials.
-
low Risky intent
intent-offensive-securitySKILL.md:189Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Malware Analysis Report
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 45/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 40Consistency. Frontmatter name (malware-analyst) differs from the folder (s3-malware-analyst)
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 85Steps. 66 steps, 1 vague phrases
- 100Execution cost. Instruction body is 1552 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
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +3Description length 349: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 66 items
- +3Output format is stated explicitly
- +4Has examples (10 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.