BF threat-detection
Use when hunting for threats in an environment, analyzing IOCs, or detecting behavioral anomalies in telemetry. Covers hypothesis-driven threat hunting, IOC sweep generation, z-score anomaly detection, and MITRE ATT&CK-mapped signal prioritization.
Covers hypothesis-driven threat hunting, IOC sweep generation, z-score anomaly detection, and MITRE ATT&CK-mapped signal prioritization.
As a process F 42/100 · Will not run — References files that are not bundled: ../incident-response/SKILL.md, ../red-team/SKILL.md, ../cloud-security/SKILL.md
How to improve
- The text references files that are not there: add them or drop the references.
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/hunt-playbooks.md:21Offensive-security / dual-use content (legitimate for authorised testing; review intended use)## Playbook 1: WMI-Based Lateral Movement
-
low Risky intent
intent-offensive-securityreferences/hunt-playbooks.md:23Offensive-security / dual-use content (legitimate for authorised testing; review intended use)**Hypothesis:** An attacker is using Windows Management Instrumentation (WMI) for remote code execution as part of lateral movement.
-
low Risky intent
intent-offensive-securityreferences/hunt-playbooks.md:35Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)3. Cross-reference source host with authentication logs for lateral movement source identification
detector -
low Risky intent
intent-offensive-securityreferences/hunt-playbooks.md:49Offensive-security / dual-use content (legitimate for authorised testing; review intended use)**Hypothesis:** An attacker is using legitimate Windows binaries (`certutil.exe`, `regs…exe`, `mshta.exe`, `msiexec.exe`) for payload delivery or execution, bypassing application allowlisting.
-
low Risky intent
intent-offensive-securityreferences/hunt-playbooks.md:116Offensive-security / dual-use content (legitimate for authorised testing; review intended use)## Playbook 4: Pass-the-Hash Lateral Movement
-
low Risky intent
intent-offensive-securitySKILL.md:8Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)Threat detection skill for proactive discovery of attacker activity through hypothesis-driven hunting, IOC analysis, and behavioral anomaly detection. This is NOT incident response (see incident-respo
detector -
low Risky intent
intent-offensive-securitySKILL.md:55Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)--hypothesis "Lateral movement via PtH using compromised service account" \
quoted -
low Risky intent
intent-offensive-securitySKILL.md:118Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| WMI lateral movement via remote execution | T1047 | WMI logs, EDR process telemetry | WMI process spawned from WINRM, unusual parent-child chain |
-
low Risky intent
intent-offensive-securitySKILL.md:121Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Pass-the-Hash lateral movement | T1550.002 | Windows security event 4624 type 3 | NTLM auth from unexpected source host to admin share |
-
low Risky intent
intent-offensive-securitySKILL.md:173Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Service account | Auth events per hour | Credential stuffing, lateral movement |
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../incident-response/SKILL.md - warning
missing-refreference to a missing file: ../red-team/SKILL.md - warning
missing-refreference to a missing file: ../cloud-security/SKILL.md - warning
missing-refreference to a missing file: ../security-pen-testing/SKILL.md
Process rating: all ten parameters 42/100
Will not run. References files that are not bundled: ../incident-response/SKILL.md, ../red-team/SKILL.md, ../cloud-security/SKILL.md
- 0Tools and files. 4 referenced file(s) missing: ../incident-response/SKILL.md, ../red-team/SKILL.md, ../cloud-security/SKILL.md
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 32 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3450 tokens
- 100Progress reporting. Reports progress
- low 11 top-level sections: this looks like several domains in one skill
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
- +1No license
- +2Single-language instructions
- +3Description length 248: enough signal without eating the budget
- +4Structure: 30 headings
- +3Step-by-step instructions: 32 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.