AB hexstrike
Cybersecurity assistant for CTF challenges, penetration testing, network recon, vulnerability assessment, and security research. Use when: (1) solving CTF challenges (web, crypto, pwn, forensics, rev, OSINT, misc), (2) performing network reconnaissance or port scanning, (3) web application security testing, (4) vulnerability scanning and assessment, (5) binary analysis or reverse engineering, (6) password cracking or hash identification, (7) forensics analysis (file, memory, network, steganography), (8) cloud security assessment (AWS, GCP, K8s, containers), (9) OSINT gathering, (10) any offensive security or red team task. Triggers on: CTF, capture the flag, pentest, recon, nmap, exploit, vulnerability, reverse engineering, forensics, steganography, hash crack, brute force, SQL injection, XSS, buffer overflow, ROP, binary exploitation, OSINT, bug bounty, security audit, cloud security.
As a process B 74/100 · Nearly there — weak spots: inputs and preconditions, 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 · 8
✓ No critical or high findings
Medium and low: 8
-
low Risky intent
intent-offensive-securityreferences/recon-methodology.md:1Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Recon & Pentest Methodology
-
low Risky intent
intent-offensive-securityreferences/recon-methodology.md:200Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)kube-hunter --remote <TARGET> # K8s pentest
detector -
low Risky intent
intent-offensive-securityskill-card.md:2Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Hexstrike helps agents run and interpret cybersecurity workflows for CTF challenges, authorized penetration testing, reconnaissance, vulnerability assessment, forensics, reverse engineering, cloud sec
-
low Risky intent
intent-offensive-securityskill-card.md:21Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Mitigation: Use it only for CTFs, owned lab systems, scoped bug bounty work, or professional engagements with written authorization; confirm target scope before running commands. <br>
-
low Risky intent
intent-offensive-securityskill-card.md:28Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- [Recon & Pentest Methodology](references/recon-methodology.md) <br>
-
low Risky intent
intent-offensive-securitySKILL.md:3Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)description: "Cybersecurity assistant for CTF challenges, penetration testing, network recon, vulnerability assessment, and security research. Use when: (1) solving CTF challenges (web, crypto, pwn, f
quoted -
low Risky intent
intent-offensive-securitySKILL.md:46Offensive-security / dual-use content (legitimate for authorised testing; review intended use)## Recon / Pentest Workflow
-
low Risky intent
intent-offensive-securitySKILL.md:48Offensive-security / dual-use content (legitimate for authorised testing; review intended use)For reconnaissance or penetration testing engagements:
Files scanned: 6. 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 74/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 60Result and completion. Output format stated, no completion criterion
- 60Failures and branches. 2 branches
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 23 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 824 tokens
- 100Running it twice. No mutating operations
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 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)
- +3Description length 898: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 12 headings
- +3Step-by-step instructions: 23 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.