SKILLEMALL.ai
GitHub ↗ RU Sign in

DF linkfox-amazon-product-selection

亚马逊选品一站式 AI 工具集，整合 竞品查询/ABA/前台/Keepa/Sorftime/Jungle Scout/卖家精灵/SIF/极目/商业洞察等 12 类工具 33 项子能力，覆盖选品、关键词、竞品、评论、利基与趋势。

ClawHub Agent Skills author: linkfox-ai v1.2.3 MIT-0 71 files · 35 scripts body ≈ 3 995 tokens Open the sourceclawhub.ai↗ analyzed 5 d ago

亚马逊选品一站式 AI 工具集，整合 竞品查询/ABA/前台/Keepa/Sorftime/Jungle Scout/卖家精灵/SIF/极目/商业洞察等 12 类工具 33 项子能力，覆盖选品、关键词、竞品、评论、利基与趋势。

As a process F 33/100 · No process to follow — References files that are not bundled: references/<源skill>.md

ProcedureData and analyticsAI and agentsWriting and documentstype 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
63/100
safety, quality, tests
Safety 60%
64
Quality 40%
61
Run on models
none yet
Process rating
F
33/100
No process to follow
References files that are not bundled: references/<源skill>.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

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".

For the author

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.

Obfuscation medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.

For the author

Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The text references files that are not there: add them or drop the references.
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 · 24

✓ No critical or high findings

Medium and low: 24
  • medium Exfiltration net-redirectable-api-key scripts/upload_image.py:21
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • medium Obfuscation obf-base64-blob SKILL.md:231
    Long base64-looking blob
    出参：`data`（nicheId/nicheTitle/translationZh/demand/productCount/avgPrice/searchVolumeWeekly/unitsSoldWeekly/brandCount/top5…are/launchRateSemiannual/cpc）、`costToken`。
  • medium Obfuscation obf-base64-blob SKILL.md:251
    Long base64-looking blob
    出参：`data[]`（每条约 37 字段：keyword/nicheName/nich…60d/nicheBrandCount/priceMinUsd/demoGenderDominant/revi…pic…），至少一个过滤条件。计费按返回条数 N（即使 N=0 也按最低计费）。
  • low Secrets in code secret-high-entropy-token references/linkfox-amazon-opportunity-search-by-metrics.md:58
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    3. **配对互补信号**：品牌级 + 产品级集中度（`feat…Lte` + `nich…Gte`）揭示"品牌分散但产品集中"——品牌延伸切入信号。
    quoted
  • low Secrets in code secret-high-entropy-token references/linkfox-amazon-opportunity-search-by-metrics.md:87
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    {"revi…pic": "size", "revi…Gte": 70, "limit": 25}
    quoted
  • low Secrets in code secret-high-entropy-token references/linkfox-amazon-opportunity-search-by-metrics.md:181
    High-entropy token-like string (may be an id, hash or a credential)
    | nich…Gte | number | 360 天市场营收下界（USD）的最小值 |
  • low Secrets in code secret-high-entropy-token references/linkfox-amazon-opportunity-search-by-metrics.md:182
    High-entropy token-like string (may be an id, hash or a credential)
    | nich…Lte | number | 360 天市场营收下界（USD）的最大值 |
  • low Secrets in code secret-high-entropy-token references/linkfox-amazon-opportunity-search-by-metrics.md:183
    High-entropy token-like string (may be an id, hash or a credential)
    | nich…Gte | number | 360 天市场营收上界（USD）的最小值 |
  • low Secrets in code secret-high-entropy-token references/linkfox-amazon-search-by-image.md:219
    High-entropy token-like string (may be an id, hash or a credential)
    | mont…Ago ~ mont…Ago | integer | 1~12月前月销量(keepa) |
  • low Secrets in code secret-high-entropy-token references/linkfox-jiimore-get-niche-info.md:178
    High-entropy token-like string (may be an id, hash or a credential)
    | sell…ore | integer | 销售伙伴数量(90天前) |
  • low Secrets in code secret-high-entropy-token references/linkfox-jiimore-get-niche-info.md:179
    High-entropy token-like string (may be an id, hash or a credential)
    | sell…ore | integer | 销售伙伴数量(360天前) |
  • low Secrets in code secret-high-entropy-token references/linkfox-jiimore-get-niche-info.md:181
    High-entropy token-like string (may be an id, hash or a credential)
    | sell…ore | integer | 销售伙伴数量(360 天统计)(90天前) |
  • low Secrets in code secret-high-entropy-token references/linkfox-jiimore-get-niche-info.md:182
    High-entropy token-like string (may be an id, hash or a credential)
    | sell…ore | integer | 销售伙伴数量(360 天统计)(360天前) |
  • low Secrets in code secret-high-entropy-token references/linkfox-jiimore-get-niche-info.md:218
    High-entropy token-like string (may be an id, hash or a credential)
    | top5…ore | number | 前5个商品所占细分市场的点击量份额(90天前) |
  • low Secrets in code secret-high-entropy-token references/linkfox-junglescout-sales-estimates.md:257
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "id": "sale…301",
    quoted
  • low Secrets in code secret-high-entropy-token references/linkfox-keepa-product-request.md:191
    High-entropy token-like string (may be an id, hash or a credential)
    | mont…Ago | integer | 10月前月销量 |
  • low Secrets in code secret-high-entropy-token references/linkfox-keepa-product-request.md:192
    High-entropy token-like string (may be an id, hash or a credential)
    | mont…Ago | integer | 11月前月销量 |
  • low Secrets in code secret-high-entropy-token references/linkfox-keepa-product-request.md:193
    High-entropy token-like string (may be an id, hash or a credential)
    | mont…Ago | integer | 12月前月销量 |
  • low Secrets in code secret-high-entropy-token references/linkfox-keepa-product-search.md:238
    High-entropy token-like string (may be an id, hash or a credential)
    | mont…Ago .. mont…Ago | integer | 最近12个月每月的月销量 |
  • low Exfiltration net-credential-use references/linkfox-sellersprite-market-research.md:318
    Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
    curl -X POST https://tool-gateway.linkfox.com/sellersprite/market/research   -H "Authorization: $LINKFOXAGENT_API_KEY"   -H "Content-Type: application/json"   -d '{
    vendor-host
  • low Exfiltration net-credential-use references/linkfox-sellersprite-traffic-keyword.md:286
    Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
    curl -X POST https://tool-gateway.linkfox.com/sellersprite/traffic/keyword   -H "Authorization: $LINKFOXAGENT_API_KEY"   -H "Content-Type: application/json"   -d '{
    vendor-host
  • low Dangerous commands cmd-shell-rc references/onboarding.md:13
    Writes to a shell startup file (quoted — discussed, not commanded)
    - macOS zsh：`echo 'export LINKFOX_AGENT_API_KEY="<key>"' >> ~/.zshrc && source ~/.zshrc`
    quoted
  • low Dangerous commands cmd-shell-rc references/onboarding.md:14
    Writes to a shell startup file (detector / deny-list definition)
    - Linux bash：`echo 'export LINKFOX_AGENT_API_KEY="<key>"' >> ~/.bashrc && source ~/.bashrc`
    detector
  • low Secrets in code secret-high-entropy-token scripts/onboarding.py:49
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    or "eyJh…iJ9")
    quoted

Files scanned: 71. 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")
  • warning missing-ref reference to a missing file: references/<源skill>.md
  • note frontmatter-key unknown frontmatter key "display_name"
  • note frontmatter-key unknown frontmatter key "display_name_en"
  • note frontmatter-key unknown frontmatter key "description_zh"
  • note frontmatter-key unknown frontmatter key "description_en"

Process rating: all ten parameters 33/100

Will not run. References files that are not bundled: references/<源skill>.md
  • 0Tools and files. 1 referenced file(s) missing: references/<源skill>.md
  • 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. 1 mutating operations with no state check
  • 100Steps. 25 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3995 tokens
  • low The response is described with custom markup (8 tags): a typed call is more reliable

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)
  • +3Description length 113: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -31 of 35 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +4Structure: 18 headings
  • +3Step-by-step instructions: 25 items
  • +4Has examples (14 code blocks)
  • +4Reference files are cited in the instructions (34 of 34)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.

External checks

ClawHub: suspicious
The skill appears to be a legitimate Amazon research integration, but it needs review because it handles credentials, persists full responses locally, and includes fallback instructions to install a remote skill package.
LLM: suspicious (high) · 14 Aug 2026