DF skillhub-publish-skill
把本地 Skill 打包并发布到 SkillHub（腾讯 skillhub.cn）与 ClawHub，覆盖预检、发布、状态回读与竞品对标全链路，并在上传被拒时用二分/ddmin 脚本把「服务端 WAF 拦内容（566）」与「包结构/字段问题」精确区分开。当用户说「发布技能到市场」「上架 skill」「SkillHub 提交失败」「Failed to fetch」「566」「上传 zip 报错」「技能审核状态」「版本号被拒」时使用。也讲清「入库成功 ≠ 已公开」——用 `mine` 的 `reviewStatus`、重发探测 `409 VERSION_EXISTS`、`/versions/<v>/signature` 三个探针判断版本到底走到哪一步。
把本地 Skill 打包并发布到 SkillHub（腾讯 skillhub.cn）与 ClawHub，覆盖预检、发布、状态回读与竞品对标全链路，并在上传被拒时用二分/ddmin 脚本把「服务端 WAF 拦内容（566）」与「包结构/字段问题」精确区分开。当用户说「发布技能到市场」「上架…
As a process F 33/100 · No process to follow — References files that are not bundled: scripts/*.py, scripts/buildkey_cdp.js, scripts/attach_debug.js
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 skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
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.
- The text references files that are not there: add them or drop the references.
- 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 · 4
✓ No critical or high findings
Medium and low: 4
-
medium Dangerous commands
cmd-pipe-to-shellreferences/cli-install.md:12Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)curl -fsSL https://skillhub.cn/install/install.sh | bash -s -- --cli-only
vendor-host -
medium Exfiltration
net-credential-usereferences/github-repo.md:15Credential used in a network call (verify the destination is the intended service)curl -o /dev/null -w "%{http_code}\n" -H "Authorization: token $TOKEN" \ -
medium Exfiltration
net-credential-usereferences/github-repo.md:75Credential used in a network call (verify the destination is the intended service)curl -s -H "Authorization: token $TOKEN" \
-
medium Dangerous commands
cmd-pipe-to-shellscripts/preflight.py:11Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)安全红线 rm -rf 家目录、curl|sh 下载执行、读取 .ssh
code literal
Files scanned: 13. 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") - warning
missing-refreference to a missing file: scripts/*.py - warning
missing-refreference to a missing file: scripts/buildkey_cdp.js - warning
missing-refreference to a missing file: scripts/attach_debug.js - warning
missing-refreference to a missing file: scripts/*.js - warning
missing-refreference to a missing file: examples/profiles/*.json - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "displayName" - note
frontmatter-keyunknown frontmatter key "summary" - note
frontmatter-keyunknown frontmatter key "subCategories" - note
frontmatter-keyunknown frontmatter key "agent_created"
Process rating: all ten parameters 33/100
- 0Tools and files. 5 referenced file(s) missing: scripts/*.py, scripts/buildkey_cdp.js, scripts/attach_debug.js
- 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. 17 mutating operations with no state check
- 100Steps. 30 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3188 tokens
- low 11 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (8 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 328: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 30 items
- +4Has examples (15 code blocks)
- +4Reference files are cited in the instructions (7 of 7)
- +3All 3 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.