BD safety-guardrails
给自主智能体/自动化流水线装上一道「预执行安全护栏」：对任何待执行动作做风险分级 （low/medium/high/critical）并给出 ALLOW / CONFIRM / DENY 决策。内置破坏性强、不可逆、 越权、外发隐私的 deny 规则与高影响 confirm 规则，强制拦截 rm -rf、强推、下载即执行、 删表、关机等高危动作，并要求用户显式确认中高危操作。适配自动化每小时触发的无人值守场景， 防止自主 agent 在没有护栏时造成不可逆损害。触发词：安全护栏、危险动作拦截、操作确认、 safety guardrails、agent 安全、预执行校验、destructive 拦截。
给自主智能体/自动化流水线装上一道「预执行安全护栏」：对任何待执行动作做风险分级 （low/medium/high/critical）并给出 ALLOW / CONFIRM / DENY 决策。内置破坏性强、不可逆、 越权、外发隐私的 deny 规则与高影响 confirm 规则，强制拦截 rm…
As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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 · 1
✓ No critical or high findings
Medium and low: 1
✓ Guard found no suspicious behaviour. 1 matches are attack strings quoted in this security skill's own documentation.
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") - note
frontmatter-keyunknown frontmatter key "agent_created" - note
frontmatter-keyunknown frontmatter key "display_name" - note
frontmatter-keyunknown frontmatter key "display_name_en" - note
frontmatter-keyunknown frontmatter key "description_zh" - note
frontmatter-keyunknown frontmatter key "description_en" - note
frontmatter-keyunknown frontmatter key "visibility"
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. 2 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, git) that frontmatter does not declare
- 100Steps. 18 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 554 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
- +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
- +1No license
- +2Single-language instructions
- +3Description length 303: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 18 items
- +4Has examples (2 code blocks)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.