DD yotta-secret
元钥 —— 跨智能体的密钥 / 凭据泄露源头扫描技能：零依赖自研用「正则 + 熵 + 格式校验」离线扫描源码 / 配置 / .env / git 历史中的疑似密钥与凭据（云厂商 API Key、私钥、口令赋值、URL 内嵌凭据、高熵长 token），输出 text / JSON / CSV，默认打码防二次泄露。触发：用户要排查代码 / 配置 / 仓库里是否泄露了 API Key、密码、私钥、token，要在提交或发布前做密钥检查，或要校验某个字符串是否为已知格式的密钥时。边界：纯本地离线扫描，不联网验证密钥是否有效、不发送任何数据；结果只是「疑似密钥」，是否真实需人工核实；仅用于已获授权 / 自有资产 / 教学环境。
元钥 —— 跨智能体的密钥 / 凭据泄露源头扫描技能：零依赖自研用「正则 + 熵 + 格式校验」离线扫描源码 / 配置 / .env / git 历史中的疑似密钥与凭据（云厂商 API Key、私钥、口令赋值、URL 内嵌凭据、高熵长 token），输出 text / JSON /…
As a process D 45/100 · 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 files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.
The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.
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.
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- 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 · 5
-
high Secrets in code
secret-private-keyreferences/rules.md:53Private key material (key header without key body)| pgp_private | PGP 私钥块 | -----BEGIN PGP PRIVATE KEY BLOCK----- … -----END PGP PRIVATE KEY BLOCK----- |
header only
Medium and low: 4
-
medium Secrets in code
secret-private-keyREADME.md:147Private key material (detector / deny-list definition; key header without key body; documentation table row)| private_key | 私钥 | `-----BEGIN PRIVATE KEY----- …
detectorheader onlytable -
medium Secrets in code
secret-private-keyREADME.zh-CN.md:148Private key material (key header without key body; documentation table row)| private_key | 私钥 | `-----BEGIN PRIVATE KEY----- …
header onlytable -
medium Secrets in code
secret-private-keyscripts/yotta_secret.py:248Private key material (detector / deny-list definition; key header without key body)r"-----BEGIN PGP PRIVATE KEY BLOCK-----.*?-----END PGP PRIVATE KEY BLOCK-----",
detectorheader only -
medium Secrets in code
secret-private-keySKILL.md:93Private key material (key header without key body; documentation table row)| private_key | 私钥 | `-----BEGIN PRIVATE KEY----- …
header onlytable
Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 312 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - warning
description-no-whenneither description nor a "## When to Use" section says when to use the skill - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "displayName" - note
frontmatter-keyunknown frontmatter key "summary" - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 45/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 29 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 993 tokens
- 100Progress reporting. Reports progress
- low 10 top-level sections: this looks like several domains in one skill
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 312: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 29 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.