AC incident-response-network
Network forensics evidence collection and analysis during security incidents. Guides volatile evidence preservation, lateral movement detection via flow records and ARP/MAC/CAM table analysis, and read-only containment verification across Cisco IOS-XE/NX-OS, Juniper JunOS, and Arista EOS. Scoped to network artifacts only — packet captures, flow data (NetFlow/sFlow/IPFIX), forwarding tables, routing state, and device logs. Not general incident response, endpoint forensics, or malware analysis.
As a process C 62/100 · Has gaps — weak spots: result and completion, when it triggers
How to improve
For the model run — optional
- 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-securityreferences/forensics-workflow.md:35Offensive-security / dual-use content (legitimate for authorised testing; review intended use)protocol analysis, malware payload extraction, credential harvesting evidence
-
low Risky intent
intent-offensive-securityreferences/forensics-workflow.md:47Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)- **Forensic value:** High — reveals communication patterns, lateral movement
detector -
low Risky intent
intent-offensive-securityreferences/forensics-workflow.md:53Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **Best for:** Lateral movement mapping, communication pattern analysis,
-
low Risky intent
intent-offensive-securityreferences/forensics-workflow.md:202Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Phase (reconnaissance, initial access, lateral movement, objective,
-
low Risky intent
intent-offensive-securityskill-card.md:2Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Network forensics evidence collection and analysis during security incidents, including volatile evidence preservation, lateral movement detection from flow and ARP/MAC/CAM data, and containment verif
-
low Risky intent
intent-offensive-securitySKILL.md:5Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Guides volatile evidence preservation, lateral movement detection via flow
-
low Risky intent
intent-offensive-securitySKILL.md:10Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Not general incident response, endpoint forensics, or malware analysis.
-
low Risky intent
intent-offensive-securitySKILL.md:25Offensive-security / dual-use content (legitimate for authorised testing; review intended use)800-61), endpoint forensics, malware analysis, or organizational
-
low Risky intent
intent-offensive-securitySKILL.md:29Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)evidence: preserve volatile data → triage scope → detect lateral movement →
detector -
low Risky intent
intent-offensive-securitySKILL.md:45Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **Lateral movement investigation** — tracing attacker movement between
Files scanned: 4. 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 62/100
- 0Result and completion. Does not say what the result is
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4806 tokens
- 85Steps. 55 steps, 1 vague phrases
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low The response is described with custom markup (10 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
- +2Single-language instructions
- +3Description length 497: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 55 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.
External checks
ClawHub: suspicious
This is a legitimate network forensics guide, but it is labeled read-only while telling users to run packet captures and save sensitive evidence files on live network devices.
LLM: suspicious (high) · VirusTotal: · 29 May 2026