CD pentest-auto
自动化渗透测试全流程：前置确认、信息收集、OWASP Top10漏洞扫描、CVE匹配验证、报告生成与docx转换。
自动化渗透测试全流程：前置确认、信息收集、OWASP Top10漏洞扫描、CVE匹配验证、报告生成与docx转换。
As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 13
✓ No critical or high findings
Medium and low: 13
-
low Secrets in code
secret-high-entropy-tokenreferences/owasp-top10-checklist.md:316High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)curl -sk -X POST -H "Content-Type: application/x-java-serialized-object" --data-binary @- "https://<target>/api/deserialize" <<< "rO0A…hcA"
detector -
low Risky intent
intent-offensive-securityskill-card.md:3Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Automates an end-to-end penetration testing workflow covering upfront scope confirmation, information gathering, OWASP Top 10 checks, CVE matching, vulnerability validation, and report conversion.
-
low Risky intent
intent-offensive-securityskill-card.md:17Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Security engineers and authorized assessors use this skill to coordinate low-concurrency penetration testing activities, collect evidence, map findings to OWASP Top 10 and known CVEs, and produce stan
-
low Risky intent
intent-offensive-securityskill-card.md:43Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- [ClawHub Skill Page](https://clawhub.ai/liuyang7792/skills/pentest-auto)
-
low Risky intent
intent-offensive-securityskill-card.md:44Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- [OWASP Top 10 Penetration Testing Checklist](references/owasp-top10-checklist.md)
-
low Risky intent
intent-offensive-securityskill-card.md:58Offensive-security / dual-use content (legitimate for authorised testing; review intended use)**Other Properties Related to Output:** [Produces penetration test evidence, OWASP coverage matrices, CVE match summaries, remediation guidance, and converted report files when pandoc is available.]
-
low Risky intent
intent-offensive-securitySKILL.md:2Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)name: "pentest-auto"
quoted -
low Risky intent
intent-offensive-securitySKILL.md:211Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)或使用脚本：`bash skills/pentest-auto/scripts/convert_report.sh <报告.md> /home/kali/ceshi/`
quoted
A further 5 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 43/100
- 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
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 100Steps. 128 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1750 tokens
- low The response is described with custom markup (14 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 57: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +4Structure: 15 headings
- +3Step-by-step instructions: 128 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 70.