AB remnux-malware-triage
perform concise malware triage, focused IOC extraction, infrastructure hunting, and markdown report writing on remnux when the user supplies a suspicious file path, archive, hash, or chat attachment. use for triage-first investigations that should prefer the remnux toolchain, identify the real payload inside archives, trace network activity and backend infrastructure, separate observed vs inferred indicators, and escalate deliberately to deeper static reversing or dynamic analysis only when justified or explicitly requested.
As a process B 71/100 · Nearly there — weak spots: result and completion, running it twice, progress reporting
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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Risky intent
intent-offensive-securityskill-card.md:2Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Provides triage-first malware analysis on REMnux, focused on identifying the primary payload, extracting IOCs, tracing infrastructure, and producing concise Markdown reports. <br>
-
low Risky intent
intent-offensive-securitySKILL.md:8Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Use this skill for **triage-first malware analysis** on REMnux.
Files scanned: 7. 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 71/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 9 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Failures and branches. 8 branches
- 100Tools and files. No external tools needed
- 100Steps. 87 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2079 tokens
- low The response is described with custom markup (3 tags): a typed call is more reliable
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)
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +3Description length 530: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 87 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.