DD gitlab-weekly-report
生成 GitLab 团队周报，支持按产品功能分类 MR、按成员和仓库汇总贡献、输出 Markdown/HTML、生成图表和历史周报首页，并可选上传到飞书文档。用于用户提到“GitLab 周报”“团队周报”“统计本周 MR/commit”“按功能归类开发工作”“生成 HTML 周报”“上传周报到飞书”等场景。 Generate GitLab weekly team reports with MR categorization, contributor and repository summaries, Markdown/HTML output, charts, historical report index pages, and optional Feishu publishing. Use when users ask for “GitLab weekly report”, “team engineering summary”, “summarize merge requests and commits”, “group work by product area”, “generate an HTML report”, or “publish the report to Feishu”.
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
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
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- 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 · 11
-
high Dangerous commands
cmd-persistencescripts/setup-cron.sh:69Persistence mechanism (cron / launchd / scheduled task / autorun registry)(crontab -l 2>/dev/null | grep -v "$CRON_COMMENT") | crontab -
-
high Dangerous commands
cmd-persistencescripts/setup-cron.sh:91Persistence mechanism (cron / launchd / scheduled task / autorun registry)(crontab -l 2>/dev/null | grep -v "$CRON_COMMENT") | crontab -
-
high Dangerous commands
cmd-persistencescripts/setup-cron.sh:94Persistence mechanism (cron / launchd / scheduled task / autorun registry)(crontab -l 2>/dev/null; echo "$CMD") | crontab -
Medium and low: 8
-
medium Exfiltration
net-credential-usescripts/lib/feishu-api.sh:31Credential used in a network call (verify the destination is the intended service)curl -s "${FEISHU_API_BASE}/docx/v1/documents/${doc_token}" \ -
low Dangerous commands
cmd-cron-mentionscripts/setup-cron.sh:64Mentions editing / listing crontabcrontab -l 2>/dev/null | grep -A2 -B2 "$CRON_COMMENT" || echo " 未找到 GitLab 周报定时任务"
-
low Dangerous commands
cmd-cron-mentionscripts/setup-cron.sh:69Mentions editing / listing crontab(crontab -l 2>/dev/null | grep -v "$CRON_COMMENT") | crontab -
-
low Dangerous commands
cmd-cron-mentionscripts/setup-cron.sh:91Mentions editing / listing crontab(crontab -l 2>/dev/null | grep -v "$CRON_COMMENT") | crontab -
-
low Dangerous commands
cmd-cron-mentionscripts/setup-cron.sh:94Mentions editing / listing crontab(crontab -l 2>/dev/null; echo "$CMD") | crontab -
-
low Dangerous commands
cmd-cron-mentionscripts/setup-cron.sh:99Mentions editing / listing crontabcrontab -l | grep -A1 -B1 "$CRON_COMMENT"
-
low Exfiltration
net-credential-usescripts/upload-to-feishu.js:270Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)return { docToken, docUrl: `https://feishu.cn/docx/${docToken}` };vendor-hostquoted -
low Exfiltration
net-credential-usescripts/upload-to-feishu.js:292Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)docUrl: `${origin}/docx/${docToken}`,quoted
Files scanned: 15. 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 46/100
- 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
- 40Consistency. Frontmatter name (gitlab-weekly-report) differs from the folder (gitlab-team-report)
- 100Tools and files. No external tools needed
- 100Steps. 33 steps
- 100Execution cost. Instruction body is 530 tokens
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -33 of 8 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 11 example trigger phrases
- +3Description length 552: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 33 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.