BF v19-trust-manifesto
Agent Community认知治理协议公开受信声明v3.3.1。行业贡献定位(规范驱动:action-ref.md源自A2A草案/标准贡献:CTEF §3.8第9个验证实现/生态共建:三方交叉验证核心参与方)+PFG临界积蓄状态(商业维度最强驱动力)+微软AGT合并+UUMit叙事。
As a process F 27/100 · Will not run — weak spots: steps, result and completion, when it triggers
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 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.
- 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 · 2
-
high Exfiltration
exfil-webhook-urlSKILL.md:64Webhook / callback URL commonly used for exfiltration (verify the destination)> 🧭 **Agent 无感接入引导页**：[Onboarding Page](https://reading-boundaries-hygiene-sheriff.trycloudflare.com/)
Medium and low: 1
-
low Exfiltration
exfil-webhook-urlskill-card.md:33Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)- [Agent Community Onboarding Page](https://reading-boundaries-hygiene-sheriff.trycloudflare.com/) <br>
placeholder
Files scanned: 3. 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 27/100
- 0Steps. Prose only: no discrete steps
- 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 (web) that frontmatter does not declare
- 70Execution cost. Instruction body is 4879 tokens
- 100Consistency. Name and required fields are in place
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)
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- -2207 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 144: enough signal without eating the budget
- +4Structure: 59 headings
- +4Has examples (5 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.