SKILLEMALL.ai
GitHub ↗ RU Sign in

CC image-fetch-toolkit

Search and fetch images from the internet for any purpose - paper figures, news photos, stock images, product photos, scientific illustrations, social media images, and more. Use this skill whenever the user needs to find, retrieve, or curate images from online sources, whether for academic papers, blog posts, presentations, marketing materials, or content creation. Also covers academic figure composition (multi-panel abc labeling), scientific illustration generation, and image search API integration.

ClawHub Agent Skills author: Haoming Yan v1.0.0 MIT-0 3 files body ≈ 4 041 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 50/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches

IntegrationResearchDesignWriting 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
66/100
safety, quality, tests
Safety 60%
54
Quality 40%
84
Run on models
none yet
Process rating
C
50/100
Has gaps
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

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

    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 · 10

    ✓ No critical or high findings

    Medium and low: 10
    • medium Exfiltration net-credential-use SKILL.md:34
      Credential used in a network call (verify the destination is the intended service)
      curl -H "Authorization: Bearer $UNSPLASH_ACCESS_KEY" \
    • medium Exfiltration net-credential-use SKILL.md:38
      Credential used in a network call (verify the destination is the intended service)
      curl -H "Authorization: Bearer $UNSPLASH_ACCESS_KEY" \
    • medium Exfiltration net-credential-use SKILL.md:42
      Credential used in a network call (verify the destination is the intended service)
      curl -H "Authorization: Bearer $UNSPLASH_ACCESS_KEY" \
    • medium Exfiltration net-credential-use SKILL.md:56
      Credential used in a network call (verify the destination is the intended service)
      curl -H "Authorization: $PEXELS_API_KEY" \
    • medium Exfiltration net-credential-use SKILL.md:60
      Credential used in a network call (verify the destination is the intended service)
      curl -H "Authorization: $PEXELS_API_KEY" \
    • medium Exfiltration exfil-secret-in-url SKILL.md:76
      Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (quoted — discussed, not commanded)
      curl "https://pixabay.com/api/?key=…&q=…&image_type=photo&per_page=10&safesearch=true"
      quoted
    • medium Exfiltration exfil-secret-in-url SKILL.md:79
      Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (quoted — discussed, not commanded)
      curl "https://pixabay.com/api/?key=…&q=robot&image_type=…&per_page=10"
      quoted
    • medium Exfiltration exfil-secret-in-url SKILL.md:82
      Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (quoted — discussed, not commanded)
      curl "https://pixabay.com/api/videos/?key=…&q=ocean&per_page=5"
      quoted
    • medium Exfiltration exfil-secret-in-url SKILL.md:95
      Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (quoted — discussed, not commanded)
      curl "https://api.flickr.com/services/rest/?method=…&api_key=…&text=…&license=…&per_page=10&format=json&nojsoncallback=1"
      quoted
    • low Exfiltration exfil-secret-in-url SKILL.md:112
      Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (destination is a well-known publishing service; quoted — discussed, not commanded)
      curl "https://www.googleapis.com/customsearch/v1?key=…&cx=…&searchType=image&q=…&num=10&imgSize=large"
      known servicequoted

    Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 50/100

    • 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
    • 0Progress reporting. Says nothing while it works
    • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 70Execution cost. Instruction body is 4041 tokens
    • 100Steps. 74 steps
    • 100Consistency. Name and required fields are in place
    • 100Running it twice. No mutating operations
    • low 12 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
    • +1No license
    • +2Single-language instructions
    • +3Description length 506: enough signal without eating the budget
    • +4Structure: 41 headings
    • +3Step-by-step instructions: 74 items
    • +4Has examples (21 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.

    External checks

    ClawHub: clean
    This is a broad but coherent image-search reference skill, with no hidden code or automatic actions, but users should be mindful of third-party API queries, credentials, licensing, and optional external tool installs.
    LLM: benign (high) · VirusTotal: · 29 May 2026