SKILLEMALL.ai
GitHub ↗ RU Sign in

CC ocas-sift

Sift: web search, research synthesis, fact verification, entity extraction, and URL content extraction. The system's general research engine. Use for ANY task requiring web information: search, research, look up, investigate, find out, check if, fact check, compare, summarize, what is, how to, product recommendations, price checks, current events, or reading a specific URL. TRIGGER ON: any question requiring current web data, any "investigate/find out/check/look into" request, any product/price/recommendation query. Do NOT use browser for search (CAPTCHA'd on VPS). The `web_search` and `web_extract` MCP tools route to SearXNG automatically — for deep research, load this skill directly. Do not use for person-focused OSINT (use Scout) or image processing (use Look).

ClawHub Agent Skills author: Indigo Karasu v2.3.1 MIT-0 41 files · 5 scripts body ≈ 3 755 tokens Open the sourceclawhub.ai↗ analyzed 6 d ago

Sift: web search, research synthesis, fact verification, entity extraction, and URL content extraction.

As a process C 58/100 · Has gaps — References files that are not bundled: scripts/*.py, references/local-business-search.md

ProcedureGitHubPlaywrightAI 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
C
88/100
safety, quality, tests
Safety 60%
94
Quality 40%
79
Run on models
none yet
Process rating
C
58/100
Has gaps
References files that are not bundled: scripts/*.py, references/local-business-search.md
Tools and files w 18
0
Inputs and preconditions w 11
0
Failures and branches w 10
50
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.

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 2

✓ No critical or high findings

Medium and low: 2
  • medium Exfiltration intent-browser-credential-store SKILL.md:48
    Accesses a browser credential / cookie store (documentation of a security skill)
    **When the user asks about products, prices, reviews, how-to advice, or any information that requires current web data, load Sift FIRST before answering from domain knowledge.** This applies even if y
    security skill

A further 1 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 39. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: scripts/*.py
  • warning missing-ref reference to a missing file: references/local-business-search.md
  • note frontmatter-key unknown frontmatter key "source"
  • note frontmatter-key unknown frontmatter key "includes"
  • note frontmatter-key unknown frontmatter key "triggers"

Process rating: all ten parameters 58/100

Will not run. References files that are not bundled: scripts/*.py, references/local-business-search.md
  • 0Tools and files. 2 referenced file(s) missing: scripts/*.py, references/local-business-search.md
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 50Failures and branches. 0 branches, has a failure section
  • 60Result and completion. Output format stated, no completion criterion
  • 85Steps. 65 steps, 2 vague phrases
  • 100When it triggers. States when to use and when not to
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3755 tokens
  • 100Running it twice. No mutating operations
  • 100Progress reporting. Reports progress
  • low 20 top-level sections: this looks like several domains in one skill
  • medium 5 test cases, all positive: not one "should refuse" or "should ask first"
  • low No test case covers injection arriving through data

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
  • -2localhost URLs: will not work for another user
  • -33 of 4 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 774: enough signal without eating the budget
  • +4Structure: 22 headings
  • +3Step-by-step instructions: 65 items
  • +3Output format is stated explicitly
  • +4Has examples (1 code blocks)
  • +4Reference files are cited in the instructions (15 of 27)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.

External checks

ClawHub: suspicious
This web-research skill is broadly useful but needs Review because it includes policy-bypass guidance, anti-bot evasion, person-profiling workflows, silent self-updates, and broad persistence.
LLM: suspicious (high) · 23 Sept 2026