BC geeknews-oss-brief
매일 GeekNews(news.hada.io)에서 오늘의 HOT 이슈 5개를 큐레이션하고, 오픈소스 출시·GitHub star 급상승 프로젝트를 우선 선정하여 텔레그램으로 전송하는 데일리 브리프 에이전트 스킬. 사용자가 "긱뉴스 요약", "오늘 개발 뉴스", "OSS 뉴스", "텔레그램 브리프", "데일리 다이제스트", "개발자 뉴스 큐레이션" 등을 언급하면 이 스킬을 사용한다. cron이나 스케줄러와 결합해 매일 오전 8시 자동 실행에도 사용한다.
As a process C 51/100 · Has gaps — 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 · 4
✓ No critical or high findings
Medium and low: 4
-
medium Exfiltration
net-credential-usereferences/telegram_setup.md:45Credential used in a network call (verify the destination is the intended service)curl -s -X POST "https://api.telegram.org/bot${TELEGRAM_BOT_TOKEN}/sendMessage" \ -
medium Exfiltration
exfil-webhook-urlscripts/send_telegram.py:24Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)url = f"https://api.telegram.org/bot{token}/sendMessage"quoted -
low Exfiltration
exfil-webhook-urlreferences/telegram_setup.md:17Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)https://api.telegram.org/bot<YOUR_TOKEN>/getUpdates
placeholder -
low Exfiltration
exfil-webhook-urlreferences/telegram_setup.md:45Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)curl -s -X POST "https://api.telegram.org/bot${TELEGRAM_BOT_TOKEN}/sendMessage" \placeholder
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 51/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 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 (geeknews-oss-brief) differs from the folder (telegram-geeknews)
- 50Failures and branches. 0 branches, has a failure section
- 100Tools and files. No external tools needed
- 100Steps. 36 steps
- 100Execution cost. Instruction body is 734 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
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 253: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 36 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.