SKILLEMALL.ai
GitHub ↗ RU Sign in

BD Gmail Assistant

Gmail API integration with smart AI features — read, send, search, and manage emails with Claude-powered summarization and drafting. Powered by evolink.ai

ClawHub Agent Skills author: EvolinkAI v1.1.1 MIT-0 15 files · 2 scripts body ≈ 1 908 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process D 44/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationGmailAI and agentsInfrastructuretype 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
B
86/100
safety, quality, tests
Safety 60%
92
Quality 40%
78
Run on models
none yet
Process rating
D
44/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
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 · 4

    ✓ No critical or high findings

    Medium and low: 4
    • medium Exfiltration net-credential-use scripts/gmail.sh:65
      Credential used in a network call (verify the destination is the intended service)
      curl -s -H "Authorization: Bearer $token" "$GMAIL_API$endpoint"
    • low Exfiltration exfil-secret-in-url scripts/gmail-auth.sh:218
      Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
      curl -s "https://oaut…com/revoke?token=…" >/dev/null 2>&1 || true
      placeholder
    • low Exfiltration net-credential-use scripts/gmail-auth.sh:218
      Credential used in a network call (verify the destination is the intended service) (destination is a well-known publishing service)
      curl -s "https://oaut…com/revoke?token=…" >/dev/null 2>&1 || true
      known service
    • low Exfiltration net-credential-use scripts/gmail.sh:140
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)
      local api_key="${EVOLINK_API_KEY:?Set EVOLINK_API_KEY for AI features. Get one at https://evolink.ai/signup}"
      vendor-hostquoted

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

    Against the Agent Skills spec

    • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)

    Process rating: all ten parameters 44/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 14 mutating operations with no state check
    • 40Consistency. Frontmatter name (Gmail Assistant) differs from the folder (gmail-assistant)
    • 55Failures and branches. 1 branches
    • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
    • 100Steps. 41 steps
    • 100Execution cost. Instruction body is 1908 tokens
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

    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
    • -41 reference files, but SKILL.md never points to them: the model will not open them
    • +1No license
    • +2Single-language instructions
    • +3Description length 154: enough signal without eating the budget
    • +4Structure: 16 headings
    • +3Step-by-step instructions: 41 items
    • +4Has examples (7 code blocks)
    • +3All 2 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.

    External checks

    ClawHub: suspicious
    The skill is a coherent Gmail assistant, but its AI script handles email text unsafely enough that a crafted email could run local code when AI features are used.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026