SKILLEMALL.ai
GitHub ↗ RU Sign in

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。

Not recommendedcritical or high security findings · low grade D
ClawHub Agent Skills author: YottaMeta v0.2.0 MIT-0 16 files · 1 script body ≈ 966 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

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

IntegrationSoftware developmentInfrastructureData and analyticstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
D
40/100
safety, quality, tests
Safety 60%
17
Quality 40%
74
Run on models
none yet
Process rating
D
45/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

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.

Secrets in code
If you install

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 If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail.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.

For the author

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

  1. 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.
  2. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
For the model run — optional
  • 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 · 34

  • high Secrets in code secret-private-key references/rules.md:53
    Private 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: 33
  • medium Secrets in code secret-private-key README.md:147
    Private 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-key README.zh-CN.md:148
    Private 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-key scripts/test_yotta_secret.py:204
    Private key material (key header without key body; test fixture / example file; quoted — discussed, not commanded)
    "-----BEGIN PRIVATE KEY----- …
    header onlyfixturequoted
  • medium Secrets in code secret-private-key scripts/test_yotta_secret.py:209
    Private key material (key header without key body; test fixture / example file; quoted — discussed, not commanded)
    "-----BEGIN PRIVATE KEY----- …
    header onlyfixturequoted
  • medium Secrets in code secret-private-key scripts/test_yotta_secret.py:214
    Private key material (key header without key body; test fixture / example file; quoted — discussed, not commanded)
    "-----BEGIN PGP PRIVATE KEY BLOCK-----\n"
    header onlyfixturequoted
  • medium Secrets in code secret-private-key scripts/test_yotta_secret.py:500
    Private key material (key header without key body; test fixture / example file; quoted — discussed, not commanded)
    pem = "-----BEGIN PRIVATE KEY----- …\n"
    header onlyfixturequoted
  • medium Secrets in code secret-private-key scripts/yotta_secret.py:227
    Private 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-key SKILL.md:88
    Private key material (key header without key body; documentation table row)
    | private_key | 私钥 | `-----BEGIN PRIVATE KEY----- …
    header onlytable
  • low Secrets in code secret-github-token scripts/test_yotta_secret.py:79
    GitHub token (placeholder value)
    "ghp_…890", "p@ssW0rd2024",
    placeholder
  • low Secrets in code secret-github-token scripts/test_yotta_secret.py:90
    GitHub token (placeholder value)
    v = "ghp_…890"
    placeholder
  • low Secrets in code secret-aws-key scripts/test_yotta_secret.py:100
    AWS access key ID (placeholder value)
    self.assertIn("aws_access_key", rule_ids("AKIA…PLE"))
    placeholder
  • low Secrets in code secret-high-entropy-token scripts/test_yotta_secret.py:110
    High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
    self.assertIn("google_api", rule_ids("AIza…tuv"))
    placeholder
  • low Secrets in code secret-google-key scripts/test_yotta_secret.py:110
    Google API key (placeholder value)
    self.assertIn("google_api", rule_ids("AIza…tuv"))
    placeholder
  • low Secrets in code secret-anthropic-key scripts/test_yotta_secret.py:118
    Anthropic API key (placeholder value)
    ids = rule_ids("sk-a…789")
    placeholder
  • low Secrets in code secret-slack-token scripts/test_yotta_secret.py:127
    Slack token (placeholder value)
    self.assertIn("slack", rule_ids("xoxb…nop"))
    placeholder
  • low Secrets in code secret-slack-token scripts/test_yotta_secret.py:128
    Slack token (placeholder value)
    self.assertIn("slack", rule_ids("xoxp…bcd"))
    placeholder
  • low Secrets in code secret-github-token scripts/test_yotta_secret.py:131
    GitHub token (placeholder value)
    self.assertIn("github", rule_ids("ghp_…890"))
    placeholder
  • low Secrets in code secret-github-token scripts/test_yotta_secret.py:132
    GitHub token (placeholder value)
    self.assertIn("github", rule_ids("gith…890"))
    placeholder
  • low Secrets in code secret-high-entropy-token scripts/test_yotta_secret.py:152
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    "SflK…w5c")
    fixturequoted
  • low Secrets in code secret-high-entropy-token scripts/test_yotta_secret.py:173
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition; test fixture / example file)
    self.assertIn("twilio", rule_ids("SK01…def"))
    detectorfixture
  • low Secrets in code secret-password-literal scripts/test_yotta_secret.py:247
    Hard-coded password / key literal (may be an example) (detector / deny-list definition; test fixture / example file)
    self.assertIn("credential", rule_ids("password = Sup3rS3cret!123"))
    detectorfixture
  • low Secrets in code secret-password-literal scripts/test_yotta_secret.py:256
    Hard-coded password / key literal (may be an example) (detector / deny-list definition; test fixture / example file)
    self.assertIn("credential", rule_ids("  client_secret: 'S0me…lue!!'"))
    detectorfixture
  • low Secrets in code secret-high-entropy-token scripts/test_yotta_secret.py:299
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    v = "Xj8m…0Mn"
    fixturequoted
  • low Secrets in code secret-labelled-token scripts/test_yotta_secret.py:330
    Labelled token / key literal (vendor format unknown — verify it is not a live credential) (test fixture / example file; quoted — discussed, not commanded)
    line = "https://example.com/api?api_key=…"
    fixturequoted
  • low Secrets in code secret-password-literal scripts/test_yotta_secret.py:330
    Hard-coded password / key literal (may be an example) (test fixture / example file; quoted — discussed, not commanded)
    line = "https://example.com/api?api_key=…"
    fixturequoted
  • low Secrets in code secret-labelled-token scripts/test_yotta_secret.py:338
    Labelled token / key literal (vendor format unknown — verify it is not a live credential) (placeholder value)
    line = "api_key = AIza…tuv"
    placeholder
  • low Secrets in code secret-high-entropy-token scripts/test_yotta_secret.py:338
    High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
    line = "api_key = AIza…tuv"
    placeholder
  • low Secrets in code secret-google-key scripts/test_yotta_secret.py:338
    Google API key (placeholder value)
    line = "api_key = AIza…tuv"
    placeholder
  • low Secrets in code secret-password-literal scripts/test_yotta_secret.py:338
    Hard-coded password / key literal (may be an example) (placeholder value)
    line = "api_key = AIza…tuv"
    placeholder
  • low Secrets in code secret-aws-key scripts/test_yotta_secret.py:344
    AWS access key ID (placeholder value)
    line = "a=AKIA…PLE b=ghp_…890"
    placeholder
  • low Secrets in code secret-github-token scripts/test_yotta_secret.py:344
    GitHub token (placeholder value)
    line = "a=AKIA…PLE b=ghp_…890"
    placeholder
  • low Secrets in code secret-aws-key scripts/test_yotta_secret.py:398
    AWS access key ID (placeholder value)
    self.write("key.txt", "AKIA…PLE\n")
    placeholder
  • low Secrets in code secret-password-literal scripts/test_yotta_secret.py:422
    Hard-coded password / key literal (may be an example) (detector / deny-list definition; test fixture / example file)
    stdin="password = Sup3rS3cret!123\n")
    detectorfixture

Files scanned: 15. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")

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 966 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
  • -31 of 2 scripts are never mentioned in SKILL.md
  • +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)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.

External checks

ClawHub: suspicious
The skill is a legitimate local secret scanner, but its default reports can expose the secrets it says are masked and can report a clean scan when requested targets were not actually scanned.
LLM: suspicious (high) · 9 Sept 2026