BC pentest-workbench
Comprehensive offensive security workflow for bug bounty, vulnerability assessment, penetration testing, and exploitation. Use when performing security testing, analyzing vulnerable targets, conducting privilege escalation, building exploits, or running reconnaissance. Covers: TCP buffer overflows (vulnserver), web application testing (VulnerableWordpress/WPScan), honeypot analysis (Cowrie), GTFOBins/LOLBAS privesc, pwn.college fundamentals, and offensive toolchain automation. Triggers on: run a pentest, exploit this, buffer overflow, privesc, OSCP, CTF, bug bounty, vulnerability assessment, rev shell, test this target.
As a process C 51/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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 · 21
✓ No critical or high findings
Medium and low: 21
-
low Risky intent
intent-offensive-securityreferences/privesc.md:1Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Privilege Escalation Reference
-
low Risky intent
intent-offensive-securityreferences/privesc.md:78Offensive-security / dual-use content (legitimate for authorised testing; review intended use)**GTFOBins search**: Filter by Function=Privilege escalation, Context=SUID
-
low Risky intent
intent-offensive-securityreferences/privesc.md:104Offensive-security / dual-use content (legitimate for authorised testing; review intended use)## Windows Privilege Escalation
-
low Risky intent
intent-offensive-securityreferences/privesc.md:108Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- `CVE-…527` (PrintNightmare) — RCE + privesc
-
low Risky intent
intent-offensive-securityreferences/privesc.md:155Offensive-security / dual-use content (legitimate for authorised testing; review intended use)## AD Privilege Escalation
-
low Risky intent
intent-offensive-securityreferences/tools-inventory.md:14Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| `theHarvester` | Pentest-Tools | Email/subdomain OSINT |
-
low Risky intent
intent-offensive-securityreferences/tools-inventory.md:15Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| `Amass` | Pentest-Tools | Subdomain enumeration |
-
low Risky intent
intent-offensive-securityreferences/tools-inventory.md:29Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| `XSStrike` | Pentest-Tools | XSS detection |
-
low Risky intent
intent-offensive-securityreferences/tools-inventory.md:30Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| `Commix` | Pentest-Tools | Command injection testing |
-
low Risky intent
intent-offensive-securityreferences/tools-inventory.md:68Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| `CrackMapExec` | Pentest-Tools | AD enum/attack tool |
-
low Risky intent
intent-offensive-securityskill-card.md:2Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Pentest Workbench guides authorized offensive security work across reconnaissance, vulnerability analysis, exploitation, privilege escalation, post-exploitation review, and documentation. <br>
-
low Risky intent
intent-offensive-securityskill-card.md:14Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Security practitioners, developers, and assessment teams use this skill to plan and document authorized penetration testing workflows, lab exploit development, reconnaissance, and privilege escalation
-
low Risky intent
intent-offensive-securityskill-card.md:28Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- [Privilege Escalation Reference](references/privesc.md) <br>
-
low Risky intent
intent-offensive-securityskill-card.md:32Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- [ClawHub skill page](https://clawhub.ai/mamuaminu/pentest-workbench) <br>
-
low Risky intent
intent-offensive-securitySKILL.md:2Offensive-security / dual-use content (legitimate for authorised testing; review intended use)name: pentest-workbench
-
low Risky intent
intent-offensive-securitySKILL.md:3Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)description: "Comprehensive offensive security workflow for bug bounty, vulnerability assessment, penetration testing, and exploitation. Use when performing security testing, analyzing vulnerable targ
quoted -
low Risky intent
intent-offensive-securitySKILL.md:6Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Pentest Workbench
-
low Risky intent
intent-offensive-securitySKILL.md:27Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)- `Pentest-Tools` (40+ categories) — scanner/framework discovery, network_enum
quoted -
low Risky intent
intent-offensive-securitySKILL.md:48Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- RCE → reverse shell via pentest-tools
A further 2 matches are quotations in this security skill's documentation and are not counted as findings.
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 51/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 46 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1030 tokens
- 100Progress reporting. Reports progress
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
- -32 of 2 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 627: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 46 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.
External checks
ClawHub: suspicious
This is a coherent penetration-testing skill, but it includes high-impact exploitation, credential-access, scanning, and post-exploitation guidance without clear authorization safeguards.
LLM: suspicious (high) · VirusTotal: · 28 May 2026